first commit

.github/FUNDING.yml

@@ -0,0 +1,3 @@
+ko_fi: xtekky
+github: [xtekky, hlohaus]
+patreon: xtekky

.github/ISSUE_TEMPLATE/default_issue.md

@@ -0,0 +1,33 @@
+---
+name: New Issue
+about: 'Please use this template !!'
+title: ''
+labels: bug
+assignees: xtekky
+
+---
+
+**Known Issues** // delete this
+- you.com issue / fix: use proxy, or vpn, your country is probably flagged
+- forefront account creation error / use your own session or wait for fix
+
+
+**Bug description**
+What did you do, what happened, which file did you try to run, in which directory
+Describe what you did after downloading repo, such as moving to this repo, running this file.
+
+ex.
+1. Go to '...'
+2. Click on '....'
+3. Scroll down to '....'
+4. See error
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**Environment**
+- python version
+- location ( are you in a cloudfare flagged country ) ?
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/workflows/close-inactive-issues.yml

@@ -0,0 +1,31 @@
+name: Close inactive issues
+
+on:
+  schedule:
+    - cron: "5 0 * * *"
+
+jobs:
+  close-issues:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - uses: actions/stale@v5
+        with:
+          days-before-issue-stale: 7
+          days-before-issue-close: 7
+          
+          days-before-pr-stale: 7
+          days-before-pr-close: 7
+          
+          stale-issue-label: "stale"
+          stale-pr-label: "stale"
+          
+          stale-issue-message: "Bumping this issue because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again."
+          close-issue-message: "Closing due to inactivity."
+          
+          stale-pr-message: "Bumping this pull request because it has been open for 7 days with no activity. Closing automatically in 7 days unless it becomes active again."
+          close-pr-message: "Closing due to inactivity."
+          
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/copilot.yml

@@ -0,0 +1,53 @@
+name: AI Code Reviewer
+
+on:
+  workflow_run:
+    workflows: ["Unittest"]
+    types:
+      - completed
+
+jobs:
+  review:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v3
+      - name: 'Download artifact'
+        uses: actions/github-script@v6
+        with:
+          script: |
+            let allArtifacts = await github.rest.actions.listWorkflowRunArtifacts({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              run_id: context.payload.workflow_run.id,
+            });
+            let matchArtifact = allArtifacts.data.artifacts.filter((artifact) => {
+              return artifact.name == "pr_number"
+            })[0];
+            let download = await github.rest.actions.downloadArtifact({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              artifact_id: matchArtifact.id,
+              archive_format: 'zip',
+            });
+            let fs = require('fs');
+            fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/pr_number.zip`, Buffer.from(download.data));
+      - name: 'Unzip artifact'
+        run: unzip pr_number.zip
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+            python-version: "3.x"
+            cache: 'pip'
+      - name: Install Requirements
+        run: |
+          pip install -r requirements.txt
+          pip install PyGithub
+      - name: AI Code Review
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY: ${{ github.repository }}
+        run: python -m etc.tool.copilot

.github/workflows/publish-to-pypi.yml

@@ -0,0 +1,52 @@
+name: Publish Python 🐍 distribution 📦 to PyPI
+
+on: push
+
+env:
+  G4F_VERSION: ${{ github.ref_name }}
+
+jobs:
+  build:
+    name: Build distribution 📦
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.x"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v3
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish distribution on PyPI 🐍
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/g4f
+    permissions:
+      id-token: write
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v3
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

.github/workflows/publish-workflow.yaml

@@ -0,0 +1,98 @@
+name: Publish Docker image
+
+on:
+  push:
+    tags:
+      - '**'
+
+jobs:
+  openapi:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.13
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.13"
+        cache: 'pip'
+    - name: Install requirements
+      run: |
+        pip install fastapi uvicorn python-multipart
+        pip install -r requirements-min.txt
+    - name: Generate openapi.json
+      run: |
+        python -m etc.tool.openapi
+    - uses: actions/upload-artifact@v4
+      with:
+        name: openapi
+        path: openapi.json
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Get metadata for Docker
+        id: metadata
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            hlohaus789/g4f
+            ghcr.io/${{ github.repository }}
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GHCR_PAT }}
+
+      - name: Build and push armv7 image
+        uses: docker/build-push-action@v5
+        with:
+            context: .
+            file: docker/Dockerfile-armv7
+            platforms: linux/arm/v7
+            push: true
+            tags: |
+              hlohaus789/g4f:latest-armv7
+              hlohaus789/g4f:${{ github.ref_name }}-armv7
+            labels: ${{ steps.metadata.outputs.labels }}
+            build-args: |
+              G4F_VERSION=${{ github.ref_name }}
+
+      - name: Build and push small images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: docker/Dockerfile-slim
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            hlohaus789/g4f:latest-slim
+            hlohaus789/g4f:${{ github.ref_name }}-slim
+          labels: ${{ steps.metadata.outputs.labels }}
+          build-args: |
+            G4F_VERSION=${{ github.ref_name }}
+
+      - name: Build and push big images
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: docker/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.metadata.outputs.tags }}
+          labels: ${{ steps.metadata.outputs.labels }}
+          build-args: |
+            G4F_VERSION=${{ github.ref_name }}

.github/workflows/unittest.yml

@@ -0,0 +1,47 @@
+name: Unittest
+
+on: 
+  pull_request:
+    types:
+      - opened
+      - synchronize
+  push:
+    branches:
+      - 'main'
+
+jobs:
+  build:
+    name: Build unittest
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.8
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.8"
+        cache: 'pip'
+    - name: Install min requirements
+      run: pip install -r requirements-min.txt
+    - name: Run tests
+      run: python -m etc.unittest
+    - name: Set up Python 3.12
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.12"
+        cache: 'pip'
+    - name: Install requirements
+      run: |
+        pip install -r requirements.txt
+        pip uninstall -y nodriver
+    - name: Run tests
+      run: python -m etc.unittest
+    - name: Save PR number
+      env:
+        PR_NUMBER: ${{ github.event.number }}
+      run: |
+        mkdir -p ./pr
+        echo $PR_NUMBER > ./pr/pr_number
+    - uses: actions/upload-artifact@v4
+      with:
+        name: pr_number
+        path: pr/

.gitignore

@@ -0,0 +1,68 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
+
+# Ignore local python virtual environment
+venv/
+
+# Ignore streamlit_chat_app.py conversations pickle
+conversations.pkl
+*.pkl
+
+# Ignore accounts created by api's
+accounts.txt
+
+.idea/
+**/__pycache__/
+__pycache__/
+
+dist/
+*.log
+*.pyc
+*.egg-info/
+*.egg
+*.egg-info
+build
+
+test.py
+update.py
+cookie.json
+notes.txt
+close_issues.py
+xxx.py
+lab.py
+lab.js
+bing.py
+bing2.py
+.DS_Store
+lab/*
+lab
+tstt.py
+providerstest.py
+prv.py
+# Emacs crap
+*~
+x.js
+x.py
+info.txt
+local.py
+*.gguf
+image.py
+.buildozer
+hardir
+har_and_cookies
+node_modules
+models
+projects/windows/g4f
+doc.txt
+dist.py
+x.txt
+bench.py
+to-reverse.txt
+g4f/Provider/OpenaiChat2.py
+generated_images/

.gitpod.yml

@@ -0,0 +1,7 @@
+# Please adjust to your needs (see https://www.gitpod.io/docs/introduction/learn-gitpod/gitpod-yaml)
+# and commit this file to your remote git repository to share the goodness with others.
+
+# Learn more from ready-to-use templates: https://www.gitpod.io/docs/introduction/getting-started/quickstart
+
+tasks:
+  - init: pip install -r requirements.txt

CODE_OF_CONDUCT.md

@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+https://t.me/xtekky.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

CONTRIBUTING.md

@@ -0,0 +1,8 @@
+<img alt="gpt4free logo" src="https://user-images.githubusercontent.com/98614666/233799515-1a7cb6a3-b17f-42c4-956d-8d2a0664466f.png">
+
+### Please, follow these steps to contribute:
+1. Reverse a website from this list: [sites-to-reverse](https://github.com/xtekky/gpt4free/issues/40)
+2. Add it to [./testing](https://github.com/xtekky/gpt4free/tree/main/testing)
+3. Refactor it and add it to [./g4f](https://github.com/xtekky/gpt4free/tree/main/g4f)
+
+### We will be grateful to see you as a contributor!

Dockerfile

@@ -1,21 +1,89 @@
-# Use the base image
-FROM hlohaus789/g4f:latest
+FROM seleniarm/node-chromium
 
-# Set working directory
-WORKDIR /app
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+ARG G4F_NO_GUI
+ARG G4F_PASS=secret
 
-# Create necessary directories
-RUN mkdir -p /app/har_and_cookies /app/generated_images
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_NO_GUI $G4F_NO_GUI
 
-# Set volume mount points
-VOLUME ["/app/har_and_cookies", "/app/generated_images"]
+ENV SE_SCREEN_WIDTH 1850
+ENV PYTHONUNBUFFERED 1
+ENV G4F_DIR /app
+ENV G4F_LOGIN_URL http://localhost:7900/?autoconnect=1&resize=scale&password=$G4F_PASS
+ENV HOME /home/$G4F_USER
+ENV PATH $PATH:$HOME/.local/bin
+ENV SE_DOWNLOAD_DIR $HOME/Downloads
+ENV SEL_USER $G4F_USER
+ENV SEL_UID $G4F_USER_ID
+ENV SEL_GID $G4F_USER_ID
 
-# Expose the specified ports 8080 1337 7900
+USER root
+
+#  If docker compose, install git
+RUN if [ "$G4F_VERSION" = "" ] ; then \
+  apt-get -qqy update && \
+  apt-get -qqy install git \
+  ; fi
+
+# Install Python3, pip, remove OpenJDK 11, clean up
+RUN apt-get -qqy update \
+  && apt-get -qqy install python3 python-is-python3 pip \
+  && apt-get -qyy remove openjdk-11-jre-headless \
+  && apt-get -qyy autoremove \
+  && apt-get -qyy clean \
+  && rm -rf /var/lib/apt/lists/* /var/cache/apt/*
+
+# Update entrypoint
+COPY docker/supervisor.conf /etc/supervisor/conf.d/selenium.conf
+COPY docker/supervisor-api.conf /etc/supervisor/conf.d/api.conf
+COPY docker/supervisor-gui.conf /etc/supervisor/conf.d/gui.conf
+
+# If no gui
+RUN if [ "$G4F_NO_GUI" ] ; then \
+  rm /etc/supervisor/conf.d/gui.conf \
+  ; fi
+
+# Change background image
+COPY docker/background.png /usr/share/images/fluxbox/ubuntu-light.png
+
+# Add user, fix permissions
+RUN groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && echo "${G4F_USER}:${G4F_PASS}" | chpasswd \
+  && mkdir "${SE_DOWNLOAD_DIR}" \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" $SE_DOWNLOAD_DIR /var/run/supervisor /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" -R /opt/bin/ /usr/bin/chromedriver /opt/selenium/
+
+# Switch user
+USER $G4F_USER_ID
+
+# Set VNC password
+RUN mkdir -p ${HOME}/.vnc \
+  && x11vnc -storepasswd ${G4F_PASS} ${HOME}/.vnc/passwd
+
+# Set the working directory in the container.
+WORKDIR $G4F_DIR
+
+# Copy the project's requirements file into the container.
+COPY requirements.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --break-system-packages --upgrade pip \
+  && pip install --break-system-packages -r requirements.txt \
+  && pip install --break-system-packages \
+    undetected-chromedriver selenium-wire \
+  && pip uninstall -y --break-system-packages \
+    pywebview plyer
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f
+
+# Expose ports
 EXPOSE 7860 
 
-# Increase shared memory size
-# Note: The actual shm-size is set at runtime with --shm-size flag
-RUN mkdir -p /dev/shm && chmod 777 /dev/shm
 
-# Default command to run the container
-CMD ["sh", "-c", "exec $CMD"]

Dockerfile copy

@@ -0,0 +1,87 @@
+FROM seleniarm/node-chromium
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+ARG G4F_NO_GUI
+ARG G4F_PASS=secret
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_NO_GUI $G4F_NO_GUI
+
+ENV SE_SCREEN_WIDTH 1850
+ENV PYTHONUNBUFFERED 1
+ENV G4F_DIR /app
+ENV G4F_LOGIN_URL http://localhost:7900/?autoconnect=1&resize=scale&password=$G4F_PASS
+ENV HOME /home/$G4F_USER
+ENV PATH $PATH:$HOME/.local/bin
+ENV SE_DOWNLOAD_DIR $HOME/Downloads
+ENV SEL_USER $G4F_USER
+ENV SEL_UID $G4F_USER_ID
+ENV SEL_GID $G4F_USER_ID
+
+USER root
+
+#  If docker compose, install git
+RUN if [ "$G4F_VERSION" = "" ] ; then \
+  apt-get -qqy update && \
+  apt-get -qqy install git \
+  ; fi
+
+# Install Python3, pip, remove OpenJDK 11, clean up
+RUN apt-get -qqy update \
+  && apt-get -qqy install python3 python-is-python3 pip \
+  && apt-get -qyy remove openjdk-11-jre-headless \
+  && apt-get -qyy autoremove \
+  && apt-get -qyy clean \
+  && rm -rf /var/lib/apt/lists/* /var/cache/apt/*
+
+# Update entrypoint
+COPY docker/supervisor.conf /etc/supervisor/conf.d/selenium.conf
+COPY docker/supervisor-api.conf /etc/supervisor/conf.d/api.conf
+COPY docker/supervisor-gui.conf /etc/supervisor/conf.d/gui.conf
+
+# If no gui
+RUN if [ "$G4F_NO_GUI" ] ; then \
+  rm /etc/supervisor/conf.d/gui.conf \
+  ; fi
+
+# Change background image
+COPY docker/background.png /usr/share/images/fluxbox/ubuntu-light.png
+
+# Add user, fix permissions
+RUN groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && echo "${G4F_USER}:${G4F_PASS}" | chpasswd \
+  && mkdir "${SE_DOWNLOAD_DIR}" \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" $SE_DOWNLOAD_DIR /var/run/supervisor /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" -R /opt/bin/ /usr/bin/chromedriver /opt/selenium/
+
+# Switch user
+USER $G4F_USER_ID
+
+# Set VNC password
+RUN mkdir -p ${HOME}/.vnc \
+  && x11vnc -storepasswd ${G4F_PASS} ${HOME}/.vnc/passwd
+
+# Set the working directory in the container.
+WORKDIR $G4F_DIR
+
+# Copy the project's requirements file into the container.
+COPY requirements.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --break-system-packages --upgrade pip \
+  && pip install --break-system-packages -r requirements.txt \
+  && pip install --break-system-packages \
+    undetected-chromedriver selenium-wire \
+  && pip uninstall -y --break-system-packages \
+    pywebview plyer
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f
+
+# Expose ports
+EXPOSE 8080 1337

Dockerfile-armv7

@@ -0,0 +1,67 @@
+FROM python:slim-bookworm
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+ARG PYDANTIC_VERSION=1.8.1
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_DIR /app
+
+RUN apt-get update && apt-get upgrade -y \
+  && apt-get install -y git \
+  && apt-get install --quiet --yes --no-install-recommends \
+      build-essential \
+# Add user and user group
+  && groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && mkdir -p /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" /var/log/supervisor \
+  && echo "${G4F_USER}:${G4F_USER}" | chpasswd \
+  && python -m pip install --upgrade pip
+
+USER $G4F_USER_ID
+WORKDIR $G4F_DIR
+
+ENV HOME /home/$G4F_USER
+ENV PATH "${HOME}/.local/bin:${PATH}"
+
+# Create app dir and copy the project's requirements file into it
+RUN mkdir -p $G4F_DIR
+COPY requirements-min.txt $G4F_DIR
+COPY requirements-slim.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --no-cache-dir -r requirements-min.txt \
+  && pip install --no-cache-dir --no-binary setuptools \
+    Cython==0.29.22 \
+    setuptools \
+  # Install PyDantic
+  && pip install \
+    -vvv \
+    --no-cache-dir \
+    --no-binary :all: \
+    --global-option=build_ext \
+    --global-option=-j8 \
+    pydantic==${PYDANTIC_VERSION}
+RUN cat requirements-slim.txt | xargs -n 1 pip install --no-cache-dir || true 
+
+# Remove build packages
+RUN pip uninstall --yes \
+      Cython \
+      setuptools
+
+USER root
+
+# Clean up build deps
+RUN apt-get purge --auto-remove --yes \
+    build-essential \
+  && apt-get clean \
+  && rm --recursive --force /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+USER $G4F_USER_ID
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f

Dockerfile-slim

@@ -0,0 +1,39 @@
+FROM python:slim-bookworm
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_DIR /app
+
+RUN apt-get update && apt-get upgrade -y \
+  && apt-get install -y git \
+# Add user and user group
+  && groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && mkdir -p /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" /var/log/supervisor \
+  && echo "${G4F_USER}:${G4F_USER}" | chpasswd \
+  && python -m pip install --upgrade pip \
+  && apt-get clean \
+  && rm --recursive --force /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+USER $G4F_USER_ID
+WORKDIR $G4F_DIR
+
+ENV HOME /home/$G4F_USER
+ENV PATH "${HOME}/.local/bin:${PATH}"
+
+# Create app dir and copy the project's requirements file into it
+RUN mkdir -p $G4F_DIR
+COPY requirements-slim.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --no-cache-dir -r requirements-slim.txt \
+  && pip install --no-cache-dir duckduckgo-search>=5.0
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f

LEGAL_NOTICE.md

@@ -0,0 +1,55 @@
+## Legal Notice
+
+This repository is **not associated with or endorsed** by the providers of the APIs contained herein. This project is intended **for educational purposes only**. It is a personal project aimed at learning and exploration. Owners of any included sites or services may contact me to improve their security or request the removal of their content from this repository.
+
+### **Affiliation Disclaimer**
+
+This repository is not associated with or endorsed by any of the API providers mentioned herein. All trademarks, API services, and other intellectual property referenced are the property of their respective owners. No claim of ownership or affiliation is made by this project.
+
+### **Liability Limitation**
+
+Under no circumstances shall the author of this repository be liable for any direct, indirect, incidental, special, consequential, or punitive damages—including but not limited to loss of profits, data, or use—arising out of or in connection with the repository. This limitation applies regardless of whether such damages were foreseeable or whether the author was advised of the possibility of such damages.
+
+### **No Warranties**
+
+This repository is provided on an "as is" and "as available" basis without any warranties of any kind, express or implied. This includes, but is not limited to, implied warranties of merchantability, fitness for a particular purpose, and non-infringement.
+
+### **User Responsibility**
+
+Users assume all risks associated with the use of this repository. They are solely responsible for any damage or loss—including financial loss—that results from the use or misuse of the repository and its contents.
+
+### **Legal Compliance**
+
+Users are responsible for ensuring that their use of the repository and its contents complies with all applicable local, state, national, and international laws and regulations.
+
+### **Indemnification**
+
+Users agree to indemnify, defend, and hold harmless the author from any claims, liabilities, damages, losses, or expenses—including legal fees—arising out of or in any way connected with their use of this repository, violation of these terms, or infringement of any intellectual property or other rights of any person or entity.
+
+### **No Endorsement**
+
+The inclusion of third-party content does not imply endorsement or recommendation of such content by the author.
+
+### **Governing Law and Jurisdiction**
+
+Any disputes arising out of or related to the use of this repository shall be governed by the laws of the author's jurisdiction, without regard to conflict of law principles.
+
+### **Severability**
+
+If any provision of this notice is found to be unlawful, void, or unenforceable, that provision shall be deemed severable from this notice and shall not affect the validity and enforceability of the remaining provisions.
+
+### **Acknowledgment of Understanding**
+
+By using this repository, users acknowledge that they have read, understood, and agree to be bound by these terms.
+
+### **Updates and Changes**
+
+The author reserves the right to modify, update, or remove any content, information, or features in this repository at any time without prior notice. Users are responsible for regularly reviewing the content and any changes made to this repository.
+
+### **Unforeseen Consequences**
+
+The author is not responsible for any consequences, damages, or losses arising from the use or misuse of this repository or the content provided by third-party APIs. Users are solely responsible for their actions and any repercussions that may follow.
+
+### **Educational Purpose**
+
+This project and its content are provided strictly for educational purposes. Users acknowledge that they are using the APIs and models at their own risk and agree to comply with all applicable laws and regulations.

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

MANIFEST.in

@@ -0,0 +1,5 @@
+recursive-include g4f/gui/server *
+recursive-include g4f/gui/client *
+recursive-include g4f/Provider/npm *
+recursive-include g4f/Provider/gigachat_crt *
+recursive-include g4f/Provider/you *

SECURITY.md

@@ -0,0 +1,4 @@
+## Reporting a Vulnerability
+
+Reporting a Vulnerability
+Please report (suspected) security vulnerabilities to https://t.me/xtekky. You will receive a response within 48 hours. If the issue is confirmed, we will release a patch as soon as possible depending on complexity but historically within a few days.

docker-compose-slim.yml

@@ -0,0 +1,25 @@
+version: '3'
+
+services:
+  g4f-gui:
+    container_name: g4f-gui
+    image: hlohaus789/g4f:slim
+    build:
+      context: .
+      dockerfile: docker/Dockerfile-slim
+    command: python -m g4f.cli gui -debug
+    volumes:
+      - .:/app
+    ports:
+      - '8080:8080'
+  g4f-api:
+    container_name: g4f-api
+    image: hlohaus789/g4f:slim
+    build:
+      context: .
+      dockerfile: docker/Dockerfile-slim
+    command: python -m g4f.cli api
+    volumes:
+      - .:/app
+    ports:
+      - '1337:1337'

docker-compose.yml

@@ -0,0 +1,17 @@
+version: '3'
+
+services:
+  gpt4free:
+    image: hlohaus789/g4f:latest
+    shm_size: 2gb
+    build:
+      context: .
+      dockerfile: docker/Dockerfile
+    volumes:
+      - .:/app
+    ports:
+      - '8080:8080'
+      - '1337:1337'
+      - '7900:7900'
+    environment:
+      - OLLAMA_HOST=host.docker.internal

docker/Dockerfile

@@ -0,0 +1,87 @@
+FROM seleniarm/node-chromium
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+ARG G4F_NO_GUI
+ARG G4F_PASS=secret
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_NO_GUI $G4F_NO_GUI
+
+ENV SE_SCREEN_WIDTH 1850
+ENV PYTHONUNBUFFERED 1
+ENV G4F_DIR /app
+ENV G4F_LOGIN_URL http://localhost:7900/?autoconnect=1&resize=scale&password=$G4F_PASS
+ENV HOME /home/$G4F_USER
+ENV PATH $PATH:$HOME/.local/bin
+ENV SE_DOWNLOAD_DIR $HOME/Downloads
+ENV SEL_USER $G4F_USER
+ENV SEL_UID $G4F_USER_ID
+ENV SEL_GID $G4F_USER_ID
+
+USER root
+
+#  If docker compose, install git
+RUN if [ "$G4F_VERSION" = "" ] ; then \
+  apt-get -qqy update && \
+  apt-get -qqy install git \
+  ; fi
+
+# Install Python3, pip, remove OpenJDK 11, clean up
+RUN apt-get -qqy update \
+  && apt-get -qqy install python3 python-is-python3 pip \
+  && apt-get -qyy remove openjdk-11-jre-headless \
+  && apt-get -qyy autoremove \
+  && apt-get -qyy clean \
+  && rm -rf /var/lib/apt/lists/* /var/cache/apt/*
+
+# Update entrypoint
+COPY docker/supervisor.conf /etc/supervisor/conf.d/selenium.conf
+COPY docker/supervisor-api.conf /etc/supervisor/conf.d/api.conf
+COPY docker/supervisor-gui.conf /etc/supervisor/conf.d/gui.conf
+
+# If no gui
+RUN if [ "$G4F_NO_GUI" ] ; then \
+  rm /etc/supervisor/conf.d/gui.conf \
+  ; fi
+
+# Change background image
+COPY docker/background.png /usr/share/images/fluxbox/ubuntu-light.png
+
+# Add user, fix permissions
+RUN groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && echo "${G4F_USER}:${G4F_PASS}" | chpasswd \
+  && mkdir "${SE_DOWNLOAD_DIR}" \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" $SE_DOWNLOAD_DIR /var/run/supervisor /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" -R /opt/bin/ /usr/bin/chromedriver /opt/selenium/
+
+# Switch user
+USER $G4F_USER_ID
+
+# Set VNC password
+RUN mkdir -p ${HOME}/.vnc \
+  && x11vnc -storepasswd ${G4F_PASS} ${HOME}/.vnc/passwd
+
+# Set the working directory in the container.
+WORKDIR $G4F_DIR
+
+# Copy the project's requirements file into the container.
+COPY requirements.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --break-system-packages --upgrade pip \
+  && pip install --break-system-packages -r requirements.txt \
+  && pip install --break-system-packages \
+    undetected-chromedriver selenium-wire \
+  && pip uninstall -y --break-system-packages \
+    pywebview plyer
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f
+
+# Expose ports
+EXPOSE 8080 1337

docker/Dockerfile-armv7

@@ -0,0 +1,67 @@
+FROM python:slim-bookworm
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+ARG PYDANTIC_VERSION=1.8.1
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_DIR /app
+
+RUN apt-get update && apt-get upgrade -y \
+  && apt-get install -y git \
+  && apt-get install --quiet --yes --no-install-recommends \
+      build-essential \
+# Add user and user group
+  && groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && mkdir -p /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" /var/log/supervisor \
+  && echo "${G4F_USER}:${G4F_USER}" | chpasswd \
+  && python -m pip install --upgrade pip
+
+USER $G4F_USER_ID
+WORKDIR $G4F_DIR
+
+ENV HOME /home/$G4F_USER
+ENV PATH "${HOME}/.local/bin:${PATH}"
+
+# Create app dir and copy the project's requirements file into it
+RUN mkdir -p $G4F_DIR
+COPY requirements-min.txt $G4F_DIR
+COPY requirements-slim.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --no-cache-dir -r requirements-min.txt \
+  && pip install --no-cache-dir --no-binary setuptools \
+    Cython==0.29.22 \
+    setuptools \
+  # Install PyDantic
+  && pip install \
+    -vvv \
+    --no-cache-dir \
+    --no-binary :all: \
+    --global-option=build_ext \
+    --global-option=-j8 \
+    pydantic==${PYDANTIC_VERSION}
+RUN cat requirements-slim.txt | xargs -n 1 pip install --no-cache-dir || true 
+
+# Remove build packages
+RUN pip uninstall --yes \
+      Cython \
+      setuptools
+
+USER root
+
+# Clean up build deps
+RUN apt-get purge --auto-remove --yes \
+    build-essential \
+  && apt-get clean \
+  && rm --recursive --force /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+USER $G4F_USER_ID
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f

docker/Dockerfile-slim

@@ -0,0 +1,39 @@
+FROM python:slim-bookworm
+
+ARG G4F_VERSION
+ARG G4F_USER=g4f
+ARG G4F_USER_ID=1000
+
+ENV G4F_VERSION $G4F_VERSION
+ENV G4F_USER $G4F_USER
+ENV G4F_USER_ID $G4F_USER_ID
+ENV G4F_DIR /app
+
+RUN apt-get update && apt-get upgrade -y \
+  && apt-get install -y git \
+# Add user and user group
+  && groupadd -g $G4F_USER_ID $G4F_USER \
+  && useradd -rm -G sudo -u $G4F_USER_ID -g $G4F_USER_ID $G4F_USER \
+  && mkdir -p /var/log/supervisor \
+  && chown "${G4F_USER_ID}:${G4F_USER_ID}" /var/log/supervisor \
+  && echo "${G4F_USER}:${G4F_USER}" | chpasswd \
+  && python -m pip install --upgrade pip \
+  && apt-get clean \
+  && rm --recursive --force /var/lib/apt/lists/* /tmp/* /var/tmp/*
+
+USER $G4F_USER_ID
+WORKDIR $G4F_DIR
+
+ENV HOME /home/$G4F_USER
+ENV PATH "${HOME}/.local/bin:${PATH}"
+
+# Create app dir and copy the project's requirements file into it
+RUN mkdir -p $G4F_DIR
+COPY requirements-slim.txt $G4F_DIR
+
+# Upgrade pip for the latest features and install the project's Python dependencies.
+RUN pip install --no-cache-dir -r requirements-slim.txt \
+  && pip install --no-cache-dir duckduckgo-search>=5.0
+
+# Copy the entire package into the container.
+ADD --chown=$G4F_USER:$G4F_USER g4f $G4F_DIR/g4f

docker/supervisor-api.conf

@@ -0,0 +1,12 @@
+[program:g4f-api]
+priority=15
+command=python -m g4f.cli api
+directory=/app
+stopasgroup=true
+autostart=true
+autorestart=true
+
+;Logs (all Hub activity redirected to stdout so it can be seen through "docker logs"
+redirect_stderr=true
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0

docker/supervisor-gui.conf

@@ -0,0 +1,12 @@
+[program:g4f-gui]
+priority=15
+command=python -m g4f.cli gui -debug
+directory=/app
+stopasgroup=true
+autostart=true
+autorestart=true
+
+;Logs (all Hub activity redirected to stdout so it can be seen through "docker logs"
+redirect_stderr=true
+stdout_logfile=/dev/stdout
+stdout_logfile_maxbytes=0

docker/supervisor.conf

@@ -0,0 +1,50 @@
+[program:xvfb]
+priority=0
+command=/opt/bin/start-xvfb.sh
+autostart=true
+autorestart=true
+
+;Logs
+redirect_stderr=false
+stdout_logfile=/var/log/supervisor/xvfb-stdout.log
+stderr_logfile=/var/log/supervisor/xvfb-stderr.log
+stdout_logfile_maxbytes=50MB
+stderr_logfile_maxbytes=50MB
+stdout_logfile_backups=5
+stderr_logfile_backups=5
+stdout_capture_maxbytes=50MB
+stderr_capture_maxbytes=50MB
+
+[program:vnc]
+priority=5
+command=/opt/bin/start-vnc.sh
+autostart=true
+autorestart=true
+
+;Logs
+redirect_stderr=false
+stdout_logfile=/var/log/supervisor/vnc-stdout.log
+stderr_logfile=/var/log/supervisor/vnc-stderr.log
+stdout_logfile_maxbytes=50MB
+stderr_logfile_maxbytes=50MB
+stdout_logfile_backups=5
+stderr_logfile_backups=5
+stdout_capture_maxbytes=50MB
+stderr_capture_maxbytes=50MB
+
+[program:novnc]
+priority=10
+command=/opt/bin/start-novnc.sh
+autostart=true
+autorestart=true
+
+;Logs
+redirect_stderr=false
+stdout_logfile=/var/log/supervisor/novnc-stdout.log
+stderr_logfile=/var/log/supervisor/novnc-stderr.log
+stdout_logfile_maxbytes=50MB
+stderr_logfile_maxbytes=50MB
+stdout_logfile_backups=5
+stderr_logfile_backups=5
+stdout_capture_maxbytes=50MB
+stderr_capture_maxbytes=50MB

docs/async_client.md

@@ -0,0 +1,400 @@
+
+# G4F - AsyncClient API Guide
+The G4F AsyncClient API is a powerful asynchronous interface for interacting with various AI models. This guide provides comprehensive information on how to use the API effectively, including setup, usage examples, best practices, and important considerations for optimal performance.
+
+
+## Compatibility Note
+The G4F AsyncClient API is designed to be compatible with the OpenAI API, making it easy for developers familiar with OpenAI's interface to transition to G4F.
+
+## Table of Contents
+   - [Introduction](#introduction)
+   - [Key Features](#key-features)
+   - [Getting Started](#getting-started)
+   - [Initializing the Client](#initializing-the-client)
+   - [Creating Chat Completions](#creating-chat-completions)
+   - [Configuration](#configuration)
+   - [Usage Examples](#usage-examples)
+   - [Text Completions](#text-completions)
+   - [Streaming Completions](#streaming-completions)
+   - [Using a Vision Model](#using-a-vision-model)
+   - [Image Generation](#image-generation)
+   - [Concurrent Tasks](#concurrent-tasks-with-asynciogather)
+   - [Available Models and Providers](#available-models-and-providers)
+   - [Error Handling and Best Practices](#error-handling-and-best-practices)
+   - [Rate Limiting and API Usage](#rate-limiting-and-api-usage)
+   - [Conclusion](#conclusion)
+
+  
+
+## Introduction
+The G4F AsyncClient API is an asynchronous version of the standard G4F Client API. It offers the same functionality as the synchronous API but with improved performance due to its asynchronous nature. This guide will walk you through the key features and usage of the G4F AsyncClient API.
+  
+
+## Key Features
+   - **Custom Providers**: Use custom providers for enhanced flexibility.
+   - **ChatCompletion Interface**: Interact with chat models through the ChatCompletion class.
+   - **Streaming Responses**: Get responses iteratively as they are received.
+   - **Non-Streaming Responses**: Generate complete responses in a single call.
+   - **Image Generation and Vision Models**: Support for image-related tasks.
+
+  
+
+## Getting Started
+### Initializing the AsyncClient
+**To use the G4F `AsyncClient`, create a new instance:**
+```python
+from g4f.client import AsyncClient
+from g4f.Provider import OpenaiChat, Gemini
+
+client = AsyncClient(
+    provider=OpenaiChat,
+    image_provider=Gemini,
+    # Add other parameters as needed
+)
+```
+
+
+## Creating Chat Completions
+**Here’s an improved example of creating chat completions:**
+```python
+response = await client.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test"
+        }
+    ]
+     # Add other parameters as needed
+)
+```
+
+**This example:**
+   - Asks a specific question `Say this is a test`
+   - Configures various parameters like temperature and max_tokens for more control over the output
+   - Disables streaming for a complete response
+
+You can adjust these parameters based on your specific needs.
+  
+
+### Configuration
+**Configure the `AsyncClient` with additional settings:**
+```python
+client = AsyncClient(
+    api_key="your_api_key_here",
+    proxies="http://user:pass@host",
+    # Add other parameters as needed
+)
+```
+
+  
+
+## Usage Examples
+### Text Completions
+**Generate text completions using the ChatCompletions endpoint:**
+```python
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient()
+    
+    response = await client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[
+            {
+                "role": "user",
+                "content": "Say this is a test"
+            }
+        ]
+    )
+    
+    print(response.choices[0].message.content)
+
+asyncio.run(main())
+```
+
+  
+
+### Streaming Completions
+**Process responses incrementally as they are generated:**
+```python
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient()
+
+    stream = client.chat.completions.create(
+        model="gpt-4",
+        messages=[
+            {
+                "role": "user",
+                "content": "Say this is a test"
+            }
+        ],
+        stream=True,
+    )
+    
+    async for chunk in stream:
+        if chunk.choices and chunk.choices[0].delta.content:
+            print(chunk.choices[0].delta.content, end="")
+
+asyncio.run(main())
+```
+
+  
+
+### Using a Vision Model
+**Analyze an image and generate a description:**
+```python
+import g4f
+import requests
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient(
+        provider=g4f.Provider.CopilotAccount
+    )
+
+    image = requests.get("https://raw.githubusercontent.com/xtekky/gpt4free/refs/heads/main/docs/cat.jpeg", stream=True).raw
+
+    response = await client.chat.completions.create(
+        model=g4f.models.default,
+        messages=[
+            {
+                "role": "user",
+                "content": "What's in this image?"
+            }
+        ],
+        image=image
+    )
+
+    print(response.choices[0].message.content)
+
+asyncio.run(main())
+```
+
+  
+
+### Image Generation
+**Generate images using a specified prompt:**
+```python
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient()
+    
+    response = await client.images.generate(
+        prompt="a white siamese cat",
+        model="flux"
+    )
+    
+    image_url = response.data[0].url
+    print(f"Generated image URL: {image_url}")
+
+asyncio.run(main())
+```
+
+  
+
+#### Base64 Response Format
+```python
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient()
+    
+    response = await client.images.generate(
+        prompt="a white siamese cat",
+        model="flux",
+        response_format="b64_json"
+    )
+    
+    base64_text = response.data[0].b64_json
+    print(base64_text)
+
+asyncio.run(main())
+```
+
+  
+
+### Concurrent Tasks with asyncio.gather
+**Execute multiple tasks concurrently:**
+```python
+import asyncio
+from g4f.client import AsyncClient
+
+async def main():
+    client = AsyncClient()
+    
+    task1 = client.chat.completions.create(
+        model=None,
+        messages=[
+            {
+                "role": "user",
+                "content": "Say this is a test"
+            }
+        ]
+    )
+    
+    task2 = client.images.generate(
+        model="flux",
+        prompt="a white siamese cat"
+    )
+    
+    try:
+        chat_response, image_response = await asyncio.gather(task1, task2)
+        
+        print("Chat Response:")
+        print(chat_response.choices[0].message.content)
+        
+        print("\nImage Response:")
+        print(image_response.data[0].url)
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+asyncio.run(main())
+```
+
+  
+
+## Available Models and Providers
+The G4F AsyncClient supports a wide range of AI models and providers, allowing you to choose the best option for your specific use case. **Here's a brief overview of the available models and providers:**
+
+### Models
+   - GPT-3.5-Turbo
+   - GPT-4o-Mini
+   - GPT-4
+   - DALL-E 3
+   - Gemini
+   - Claude (Anthropic)
+   - And more...
+
+  
+
+### Providers
+   - OpenAI
+   - Google (for Gemini)
+   - Anthropic
+   - Microsoft Copilot 
+   - Custom providers
+
+
+**To use a specific model or provider, specify it when creating the client or in the API call:**
+```python
+client = AsyncClient(provider=g4f.Provider.OpenaiChat)
+
+# or
+
+response = await client.chat.completions.create(
+    model="gpt-4",
+    provider=g4f.Provider.Bing,
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello, world!"
+        }
+    ]
+)
+```
+
+  
+
+## Error Handling and Best Practices
+Implementing proper error handling and following best practices is crucial when working with the G4F AsyncClient API. This ensures your application remains robust and can gracefully handle various scenarios. **Here are some key practices to follow:**
+
+1. **Use try-except blocks to catch and handle exceptions:**
+```python
+try:
+    response = await client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[
+            {
+                "role": "user",
+                "content": "Hello, world!"
+            }
+        ]
+    )
+except Exception as e:
+    print(f"An error occurred: {e}")
+```
+
+2. **Check the response status and handle different scenarios:**
+```python
+if response.choices:
+    print(response.choices[0].message.content)
+else:
+    print("No response generated")
+```
+
+3. **Implement retries for transient errors:**
+```python
+import asyncio
+from tenacity import retry, stop_after_attempt, wait_exponential
+
+@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10))
+async def make_api_call():
+    # Your API call here
+    pass
+```
+
+  
+
+## Rate Limiting and API Usage
+When working with the G4F AsyncClient API, it's important to implement rate limiting and monitor your API usage. This helps ensure fair usage, prevents overloading the service, and optimizes your application's performance. Here are some key strategies to consider:
+  
+
+1. **Implement rate limiting in your application:**
+```python
+import asyncio
+from aiolimiter import AsyncLimiter
+
+rate_limit = AsyncLimiter(max_rate=10, time_period=1)  # 10 requests per second
+
+async def make_api_call():
+    async with rate_limit:
+        # Your API call here
+        pass
+```
+
+  
+
+2. **Monitor your API usage and implement logging:**
+```python
+import logging
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+async def make_api_call():
+    try:
+        response = await client.chat.completions.create(...)
+        logger.info(f"API call successful. Tokens used: {response.usage.total_tokens}")
+    except Exception as e:
+        logger.error(f"API call failed: {e}")
+```
+
+  
+
+3. **Use caching to reduce API calls for repeated queries:**
+```python
+from functools import lru_cache
+
+@lru_cache(maxsize=100)
+def get_cached_response(query):
+    # Your API call here
+    pass
+```
+
+## Conclusion
+The G4F AsyncClient API provides a powerful and flexible way to interact with various AI models asynchronously. By leveraging its features and following best practices, you can build efficient and responsive applications that harness the power of AI for text generation, image analysis, and image creation.
+
+Remember to handle errors gracefully, implement rate limiting, and monitor your API usage to ensure optimal performance and reliability in your applications.
+
+---
+
+[Return to Home](/)

docs/client.md

@@ -0,0 +1,334 @@
+
+# G4F Client API Guide
+ 
+
+## Table of Contents
+   - [Introduction](#introduction)
+   - [Getting Started](#getting-started)
+   - [Switching to G4F Client](#switching-to-g4f-client)
+   - [Initializing the Client](#initializing-the-client)
+   - [Creating Chat Completions](#creating-chat-completions)
+   - [Configuration](#configuration)
+   - [Usage Examples](#usage-examples)
+   - [Text Completions](#text-completions)
+   - [Streaming Completions](#streaming-completions)
+   - [Image Generation](#image-generation)
+   - [Creating Image Variations](#creating-image-variations)
+   - [Advanced Usage](#advanced-usage)
+   - [Using a List of Providers with RetryProvider](#using-a-list-of-providers-with-retryprovider)
+   - [Using GeminiProVision](#using-geminiprovision)
+   - [Using a Vision Model](#using-a-vision-model)
+   - [Command-line Chat Program](#command-line-chat-program)
+
+  
+
+## Introduction
+Welcome to the G4F Client API, a cutting-edge tool for seamlessly integrating advanced AI capabilities into your Python applications. This guide is designed to facilitate your transition from using the OpenAI client to the G4F Client, offering enhanced features while maintaining compatibility with the existing OpenAI API.
+
+## Getting Started
+### Switching to G4F Client
+**To begin using the G4F Client, simply update your import statement in your Python code:**
+
+**Old Import:**
+```python
+from openai import OpenAI
+```
+
+  
+
+**New Import:**
+```python
+from g4f.client import Client as OpenAI
+```
+
+  
+
+The G4F Client preserves the same familiar API interface as OpenAI, ensuring a smooth transition process.
+
+## Initializing the Client
+To utilize the G4F Client, create a new instance. **Below is an example showcasing custom providers:**
+```python
+from g4f.client import Client
+from g4f.Provider import BingCreateImages, OpenaiChat, Gemini
+
+client = Client(
+    provider=OpenaiChat,
+    image_provider=Gemini,
+    # Add any other necessary parameters
+)
+```
+
+## Creating Chat Completions
+**Here’s an improved example of creating chat completions:**
+```python
+response = client.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test"
+        }
+    ]
+    # Add any other necessary parameters
+)
+```
+
+**This example:**
+   - Asks a specific question `Say this is a test`
+   - Configures various parameters like temperature and max_tokens for more control over the output
+   - Disables streaming for a complete response
+
+You can adjust these parameters based on your specific needs.
+ 
+
+## Configuration
+**You can set an `api_key` for your provider in the client and define a proxy for all outgoing requests:**
+```python
+from g4f.client import Client
+
+client = Client(
+    api_key="your_api_key_here",
+    proxies="http://user:pass@host",
+    # Add any other necessary parameters
+)
+```
+
+  
+
+## Usage Examples
+### Text Completions
+**Generate text completions using the `ChatCompletions` endpoint:** 
+```python
+from g4f.client import Client
+
+client = Client()
+
+response = client.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test"
+        }
+    ]
+    # Add any other necessary parameters
+)
+
+print(response.choices[0].message.content)
+```
+
+  
+
+### Streaming Completions
+**Process responses incrementally as they are generated:**
+```python
+from g4f.client import Client
+
+client = Client()
+
+stream = client.chat.completions.create(
+    model="gpt-4",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test"
+        }
+    ],
+    stream=True,
+)
+
+for chunk in stream:
+    if chunk.choices[0].delta.content:
+        print(chunk.choices[0].delta.content or "", end="")
+```
+
+  
+
+### Image Generation
+**Generate images using a specified prompt:**
+```python
+from g4f.client import Client
+
+client = Client()
+
+response = client.images.generate(
+    model="flux",
+    prompt="a white siamese cat"
+    # Add any other necessary parameters
+)
+
+image_url = response.data[0].url
+
+print(f"Generated image URL: {image_url}")
+```
+
+
+#### Base64 Response Format
+```python
+from g4f.client import Client
+
+client = Client()
+
+response = client.images.generate(
+    model="flux",
+    prompt="a white siamese cat",
+    response_format="b64_json"
+)
+
+base64_text = response.data[0].b64_json
+print(base64_text)
+```
+
+  
+
+### Creating Image Variations
+**Create variations of an existing image:**
+```python
+from g4f.client import Client
+
+client = Client()
+
+response = client.images.create_variation(
+    image=open("cat.jpg", "rb"),
+    model="bing"
+    # Add any other necessary parameters
+)
+
+image_url = response.data[0].url
+
+print(f"Generated image URL: {image_url}")
+```
+
+  
+
+## Advanced Usage
+
+### Using a List of Providers with RetryProvider
+```python
+from g4f.client import Client
+from g4f.Provider import RetryProvider, Phind, FreeChatgpt, Liaobots
+import g4f.debug
+
+g4f.debug.logging = True
+g4f.debug.version_check = False
+
+client = Client(
+    provider=RetryProvider([Phind, FreeChatgpt, Liaobots], shuffle=False)
+)
+
+response = client.chat.completions.create(
+    model="",
+    messages=[
+        {
+            "role": "user",
+            "content": "Hello"
+        }
+    ]
+)
+
+print(response.choices[0].message.content)
+```
+
+  
+### Using GeminiProVision
+```python
+from g4f.client import Client
+from g4f.Provider.GeminiPro import GeminiPro
+
+client = Client(
+    api_key="your_api_key_here",
+    provider=GeminiPro
+)
+
+response = client.chat.completions.create(
+    model="gemini-pro-vision",
+    messages=[
+        {
+            "role": "user",
+            "content": "What are on this image?"
+        }
+    ],
+    image=open("docs/waterfall.jpeg", "rb")
+)
+
+print(response.choices[0].message.content)
+```
+
+  
+### Using a Vision Model
+**Analyze an image and generate a description:**
+```python
+import g4f
+import requests
+from g4f.client import Client
+
+image = requests.get("https://raw.githubusercontent.com/xtekky/gpt4free/refs/heads/main/docs/cat.jpeg", stream=True).raw
+# Or: image = open("docs/cat.jpeg", "rb")
+
+client = Client(
+    provider=CopilotAccount
+)
+
+response = client.chat.completions.create(
+    model=g4f.models.default,
+    messages=[
+        {
+            "role": "user",
+            "content": "What are on this image?"
+        }
+    ],
+    image=image
+    # Add any other necessary parameters
+)
+
+print(response.choices[0].message.content)
+```
+
+  
+## Command-line Chat Program
+**Here's an example of a simple command-line chat program using the G4F Client:**
+```python
+import g4f
+from g4f.client import Client
+
+# Initialize the GPT client with the desired provider
+client = Client()
+
+# Initialize an empty conversation history
+messages = []
+
+while True:
+    # Get user input
+    user_input = input("You: ")
+
+    # Check if the user wants to exit the chat
+    if user_input.lower() == "exit":
+        print("Exiting chat...")
+        break  # Exit the loop to end the conversation
+
+    # Update the conversation history with the user's message
+    messages.append({"role": "user", "content": user_input})
+
+    try:
+        # Get GPT's response
+        response = client.chat.completions.create(
+            messages=messages,
+            model=g4f.models.default,
+        )
+
+        # Extract the GPT response and print it
+        gpt_response = response.choices[0].message.content
+        print(f"Bot: {gpt_response}")
+
+        # Update the conversation history with GPT's response
+        messages.append({"role": "assistant", "content": gpt_response})
+
+    except Exception as e:
+        print(f"An error occurred: {e}")
+```
+ 
+This guide provides a comprehensive overview of the G4F Client API, demonstrating its versatility in handling various AI tasks, from text generation to image analysis and creation. By leveraging these features, you can build powerful and responsive applications that harness the capabilities of advanced AI models.
+
+
+---  
+[Return to Home](/)

docs/docker.md

@@ -0,0 +1,128 @@
+
+# G4F Docker Setup
+
+## Table of Contents
+   - [Prerequisites](#prerequisites)
+   - [Installation and Setup](#installation-and-setup)
+   - [Testing the API](#testing-the-api)
+   - [Troubleshooting](#troubleshooting)
+   - [Stopping the Service](#stopping-the-service)
+
+
+## Prerequisites
+**Before you begin, ensure you have the following installed on your system:**
+   - [Docker](https://docs.docker.com/get-docker/)
+   - [Docker Compose](https://docs.docker.com/compose/install/)
+   - Python 3.7 or higher
+   - pip (Python package manager)
+
+**Note:** If you encounter issues with Docker, you can run the project directly using Python.
+
+## Installation and Setup
+
+### Docker Method (Recommended)
+1. **Clone the Repository**
+   ```bash
+   git clone https://github.com/xtekky/gpt4free.git
+   cd gpt4free
+   ```
+
+2. **Build and Run with Docker Compose**
+
+   Pull the latest image and run a container with Google Chrome support:
+   ```bash
+      docker pull hlohaus789/g4f
+      docker-compose up -d
+   ```
+   Or run the small docker images without Google Chrome:
+   ```bash
+      docker-compose -f docker-compose-slim.yml up -d
+   ```
+
+3. **Access the API or the GUI**
+
+   The api server will be accessible at `http://localhost:1337`
+
+   And the gui at this url: `http://localhost:8080`
+
+### Non-Docker Method
+If you encounter issues with Docker, you can run the project directly using Python:
+
+1. **Clone the Repository**
+   ```bash
+   git clone https://github.com/xtekky/gpt4free.git
+   cd gpt4free
+   ```
+
+2. **Install Dependencies**
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+3. **Run the Server**
+   ```bash
+   python -m g4f.api.run
+   ```
+
+4. **Access the API or the GUI**
+
+   The api server will be accessible at `http://localhost:1337`
+
+   And the gui at this url: `http://localhost:8080`
+
+
+## Testing the API
+**You can test the API using curl or by creating a simple Python script:**
+### Using curl
+```bash
+curl -X POST -H "Content-Type: application/json" -d '{"prompt": "What is the capital of France?"}' http://localhost:1337/chat/completions
+```
+
+### Using Python
+**Create a file named `test_g4f.py` with the following content:**
+```python
+import requests
+
+url = "http://localhost:1337/v1/chat/completions"
+body = {
+    "model": "gpt-4o-mini", 
+    "stream": False,
+    "messages": [
+        {"role": "assistant", "content": "What can you do?"}
+    ]
+}
+
+json_response = requests.post(url, json=body).json().get('choices', [])
+
+for choice in json_response:
+    print(choice.get('message', {}).get('content', ''))
+```
+
+**Run the script:**
+```bash
+python test_g4f.py
+```
+
+## Troubleshooting
+- If you encounter issues with Docker, try running the project directly using Python as described in the Non-Docker Method.
+- Ensure that you have the necessary permissions to run Docker commands. You might need to use `sudo` or add your user to the `docker` group.
+- If the server doesn't start, check the logs for any error messages and ensure all dependencies are correctly installed.
+
+**_For more detailed information on API endpoints and usage, refer to the [G4F API documentation](docs/interference-api.md)._**
+
+
+
+## Stopping the Service
+
+### Docker Method
+**To stop the Docker containers, use the following command:**
+```bash
+docker-compose down
+```
+
+### Non-Docker Method
+If you're running the server directly with Python, you can stop it by pressing Ctrl+C in the terminal where it's running.
+
+---
+
+[Return to Home](/)

docs/git.md

@@ -0,0 +1,129 @@
+
+# G4F - Git Installation Guide
+
+This guide provides step-by-step instructions for installing G4F from the source code using Git.
+
+
+## Table of Contents
+
+1. [Prerequisites](#prerequisites)
+2. [Installation Steps](#installation-steps)
+   1. [Clone the Repository](#1-clone-the-repository)
+   2. [Navigate to the Project Directory](#2-navigate-to-the-project-directory)
+   3. [Set Up a Python Virtual Environment](#3-set-up-a-python-virtual-environment-recommended)
+   4. [Activate the Virtual Environment](#4-activate-the-virtual-environment)
+   5. [Install Dependencies](#5-install-dependencies)
+   6. [Verify Installation](#6-verify-installation)
+3. [Usage](#usage)
+4. [Troubleshooting](#troubleshooting)
+5. [Additional Resources](#additional-resources)
+
+---
+
+## Prerequisites
+
+Before you begin, ensure you have the following installed on your system:
+- Git
+- Python 3.7 or higher
+- pip (Python package installer)
+
+## Installation Steps
+
+### 1. Clone the Repository
+**Open your terminal and run the following command to clone the G4F repository:**
+```bash
+git clone https://github.com/xtekky/gpt4free.git
+```
+
+### 2. Navigate to the Project Directory
+**Change to the project directory:**
+```bash
+cd gpt4free
+```
+
+### 3. Set Up a Python Virtual Environment (Recommended)
+**It's best practice to use a virtual environment to manage project dependencies:**
+```bash
+python3 -m venv venv
+```
+
+### 4. Activate the Virtual Environment
+**Activate the virtual environment based on your operating system:**
+- **Windows:**
+  ```bash
+  .\venv\Scripts\activate
+  ```
+
+- **macOS and Linux:**
+  ```bash
+  source venv/bin/activate
+  ```
+
+### 5. Install Dependencies
+**You have two options for installing dependencies:**
+
+#### Option A: Install Minimum Requirements
+**For a lightweight installation, use:**
+```bash
+pip install -r requirements-min.txt
+```
+
+#### Option B: Install All Packages
+**For a full installation with all features, use:**
+```bash
+pip install -r requirements.txt
+```
+
+### 6. Verify Installation
+You can now create Python scripts and utilize the G4F functionalities. Here's a basic example:
+
+**Create a `g4f-test.py` file in the root folder and start using the repository:**
+```python
+import g4f
+# Your code here
+```
+
+## Usage
+**After installation, you can start using G4F in your Python scripts. Here's a basic example:**
+```python
+import g4f
+
+# Your G4F code here
+# For example:
+from g4f.client import Client
+
+client = Client()
+
+response = client.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test"
+        }
+    ]
+    # Add any other necessary parameters
+)
+
+print(response.choices[0].message.content)
+```
+
+## Troubleshooting
+**If you encounter any issues during installation or usage:**
+   1. Ensure all prerequisites are correctly installed.
+   2. Check that you're in the correct directory and the virtual environment is activated.
+   3. Try reinstalling the dependencies.
+   4. Consult the [G4F documentation](https://github.com/xtekky/gpt4free) for more detailed information.
+
+## Additional Resources
+   - [G4F GitHub Repository](https://github.com/xtekky/gpt4free)
+   - [Python Virtual Environments Guide](https://docs.python.org/3/tutorial/venv.html)
+   - [pip Documentation](https://pip.pypa.io/en/stable/)
+
+---
+
+**_For more information or support, please visit the [G4F GitHub Issues page](https://github.com/xtekky/gpt4free/issues)._**
+
+
+---  
+[Return to Home](/)

docs/guides/create_provider.md

@@ -0,0 +1,62 @@
+#### Create Provider with AI Tool
+
+Call in your terminal the `create_provider` script:
+```bash
+python -m etc.tool.create_provider
+```
+1. Enter your name for the new provider.
+2. Copy and paste the `cURL` command from your browser developer tools.
+3. Let the AI ​​create the provider for you.
+4. Customize the provider according to your needs.
+
+#### Create Provider
+
+1. Check out the current [list of potential providers](https://github.com/zukixa/cool-ai-stuff#ai-chat-websites), or find your own provider source!
+2. Create a new file in [g4f/Provider](/g4f/Provider) with the name of the Provider.
+3. Implement a class that extends [BaseProvider](/g4f/providers/base_provider.py).
+
+```py
+from __future__ import annotations
+
+from ..typing import AsyncResult, Messages
+from .base_provider import AsyncGeneratorProvider
+
+class HogeService(AsyncGeneratorProvider):
+    url                   = "https://chat-gpt.com"
+    working               = True
+    supports_gpt_35_turbo = True
+
+    @classmethod
+    async def create_async_generator(
+        cls,
+        model: str,
+        messages: Messages,
+        proxy: str = None,
+        **kwargs
+    ) -> AsyncResult:
+        yield ""
+```
+
+4. Here, you can adjust the settings, for example, if the website does support streaming, set `supports_stream` to `True`...
+5. Write code to request the provider in `create_async_generator` and `yield` the response, _even if_ it's a one-time response, do not hesitate to look at other providers for inspiration.
+6. Add the Provider Import in [`g4f/Provider/__init__.py`](./g4f/Provider/__init__.py)
+
+```py
+from .HogeService import HogeService
+
+__all__ = [
+  HogeService,
+]
+```
+
+7. You are done !, test the provider by calling it:
+
+```py
+import g4f
+
+response = g4f.ChatCompletion.create(model='gpt-3.5-turbo', provider=g4f.Provider.PROVIDERNAME,
+                                    messages=[{"role": "user", "content": "test"}], stream=g4f.Provider.PROVIDERNAME.supports_stream)
+
+for message in response:
+    print(message, flush=True, end='')
+```

docs/guides/help_me.md

@@ -0,0 +1,106 @@
+### Guide: How can AI help me with writing code?
+
+🤖 Ever dreamt of writing code at lightning speed, effortlessly crafting clean, bug-free functionalities? Welcome to the age of AI-powered coding, where your imagination merges seamlessly with the machine's precision. This guide unveils 4 powerful ways AI can become your secret weapon in the coding world, saving you time, resources, and frustration. 😎
+
+- Language Agnostic? No Problem! Rewrite Code with Ease
+- Improving Written Code: Polish Your Code Like a Pro
+- Demystifying the Unreadable: Deobfuscating Unreadable Code
+- Custom Functions: Your AI-Powered Genie in a Bottle
+
+So you can streamline your coding process, improve code quality, and enhance productivity.
+
+#### 1. Rewriting Code from One Language to Another
+You can leverage AI to translate code from one programming language to another. For instance, you can easily convert JavaScript code to Python using the following approach:
+
+**Prompt:**
+```
+Rewrite this JavaScript code to Python code. Use the aiohttp package:
+```
+```javascript
+async function fetch_data(url) {
+    const response = await fetch(url);
+    const data = await response.json();
+    return data;
+}
+```
+
+**AI Response:**
+```python
+import aiohttp
+
+async def fetch_data(url):
+    async with aiohttp.ClientSession() as session:
+        async with session.get(url) as response:
+            data = await response.json()
+            return data
+```
+
+#### 2. Improving Written Code
+You can ask the AI to enhance your code by adding comments, docstrings, and type hints for better readability and maintainability.
+
+**Example Usage:**
+```
+Improve this Python code, add Google docstrings and type hints. 
+Responses with the complete code and don't use placeholders.
+Keep the comments:
+```
+```python
+def calculate_area(radius):
+    # Calculate the area of a circle
+    return 3.14 * radius ** 2
+```
+
+**AI Response:**
+```python
+def calculate_area(radius: float) -> float:
+    """Calculate the area of a circle.
+
+    Args:
+        radius (float): The radius of the circle.
+
+    Returns:
+        float: The area of the circle.
+    """
+    return 3.14 * radius ** 2
+```
+
+#### 3. Deobfuscating Unreadable Code
+AI can help in making obfuscated or unreadable code more understandable and maintainable.
+
+**Example Usage:**
+```
+Deobfuscate this JavaScript code. Improve the readability:
+```
+
+```javascript
+(function() {
+    var a = 'Hello', b = 'World';
+    console.log(a + ' ' + b);
+})();
+```
+
+**AI Response:**
+```javascript
+(function() {
+    var greeting = 'Hello';
+    var subject = 'World';
+    console.log(greeting + ' ' + subject);
+})();
+```
+
+#### 4. Writing Custom Functions
+You can also ask the AI to generate custom functions or help you with specific coding issues.
+
+**Example Usage:**
+```
+Write a function that returns the sum of two numbers.
+```
+
+**AI Response:**
+```python
+def add_numbers(a, b):
+    """Add two numbers together."""
+    return a + b
+```
+
+These are just a few ways AI can revolutionize your coding experience. As AI technology continues to evolve, the possibilities are endless. So, embrace the future, unlock the power of AI, and watch your coding potential soar! 👷‍♂️

docs/guides/phone.md

@@ -0,0 +1,50 @@
+### Guide: Running the G4F GUI on Your Smartphone
+
+Running Python applications on your smartphone is possible with specialized apps like Pydroid. This tutorial will walk you through the process using an Android smartphone with Pydroid. Note that the steps may vary slightly for iPhone users due to differences in app names and ownership.
+
+<p align="center">
+    On the first screenshot is <strong>Pydroid</strong> and on the second is the <strong>Web UI</strong> in a browser
+</p>
+
+<p align="center">
+    <img src="/docs/guides/phone.png" />
+    <img src="/docs/guides/phone2.jpeg" />
+</p>
+
+1. **Install Pydroid from the Google Play Store:**
+   - Navigate to the Google Play Store and search for "Pydroid 3 - IDE for Python 3" or use the following link: [Pydroid 3 - IDE for Python 3](https://play.google.com/store/apps/details/Pydroid_3_IDE_for_Python_3).
+
+2. **Install the Pydroid Repository Plugin:**
+   - To enhance functionality, install the Pydroid repository plugin. Find it on the Google Play Store or use this link: [Pydroid Repository Plugin](https://play.google.com/store/apps/details?id=ru.iiec.pydroid3.quickinstallrepo).
+
+3. **Adjust App Settings:**
+   - In the app settings for Pydroid, disable power-saving mode and ensure that the option to pause when not in use is also disabled. This ensures uninterrupted operation of your Python scripts.
+
+4. **Install Required Packages:**
+   - Open Pip within the Pydroid app and install these necessary packages:
+     ```
+      g4f flask pillow beautifulsoup4
+     ```
+
+5. **Create a New Python Script:**
+   - Within Pydroid, create a new Python script and input the following content:
+     ```python
+     from g4f import set_cookies
+
+     set_cookies(".bing.com", {
+         "_U": "cookie value"
+     })
+
+     from g4f.gui import run_gui
+
+     run_gui("0.0.0.0", 8080, debug=True)
+     ```
+     Replace `"cookie value"` with your actual cookie value from Bing if you intend to create images using Bing.
+
+6. **Execute the Script:**
+   - Run the script by clicking on the play button or selecting the option to execute it.
+
+7. **Access the GUI:**
+   - Wait for the server to start, and once it's running, open the GUI using the URL provided in the output. [http://localhost:8080/chat/](http://localhost:8080/chat/)
+
+By following these steps, you can successfully run the G4F GUI on your smartphone using Pydroid, allowing you to create and interact with graphical interfaces directly from your device.

docs/interference-api.md

@@ -0,0 +1,166 @@
+# G4F - Interference API Usage Guide
+  
+
+## Table of Contents
+   - [Introduction](#introduction)
+   - [Running the Interference API](#running-the-interference-api)
+   - [From PyPI Package](#from-pypi-package)
+   - [From Repository](#from-repository)
+   - [Using the Interference API](#using-the-interference-api)
+   - [Basic Usage](#basic-usage)
+   - [With OpenAI Library](#with-openai-library)
+   - [With Requests Library](#with-requests-library)
+   - [Key Points](#key-points)
+   - [Conclusion](#conclusion)
+  
+
+## Introduction
+The G4F Interference API is a powerful tool that allows you to serve other OpenAI integrations using G4F (Gpt4free). It acts as a proxy, translating requests intended for the OpenAI API into requests compatible with G4F providers. This guide will walk you through the process of setting up, running, and using the Interference API effectively.
+  
+
+## Running the Interference API
+**You can run the Interference API in two ways:** using the PyPI package or from the repository.
+  
+
+### From PyPI Package
+**To run the Interference API directly from the G4F PyPI package, use the following Python code:**
+
+```python
+from g4f.api import run_api
+
+run_api()
+```
+
+  
+### From Repository
+**If you prefer to run the Interference API from the cloned repository, you have two options:**
+
+1. **Using the command line:**
+```bash
+g4f api
+```
+
+2. **Using Python:**
+```bash
+python -m g4f.api.run
+```
+
+**Once running, the API will be accessible at:** `http://localhost:1337/v1`
+
+**(Advanced) Bind to custom port:**
+```bash
+python -m g4f.cli api --bind "0.0.0.0:2400" 
+```
+
+## Using the Interference API
+
+### Basic Usage
+**You can interact with the Interference API using curl commands for both text and image generation:**
+
+**For text generation:**
+```bash
+curl -X POST "http://localhost:1337/v1/chat/completions" \
+     -H "Content-Type: application/json" \
+     -d '{
+           "messages": [
+             {
+               "role": "user",
+               "content": "Hello"
+             }
+           ],
+           "model": "gpt-4o-mini"
+         }'
+```
+
+**For image generation:**
+1. **url:**
+```bash
+curl -X POST "http://localhost:1337/v1/images/generate" \
+     -H "Content-Type: application/json" \
+     -d '{
+           "prompt": "a white siamese cat",
+           "model": "flux",
+           "response_format": "url"
+         }'
+```
+
+2. **b64_json**
+```bash
+curl -X POST "http://localhost:1337/v1/images/generate" \
+     -H "Content-Type: application/json" \
+     -d '{
+           "prompt": "a white siamese cat",
+           "model": "flux",
+           "response_format": "b64_json"
+         }'
+```
+
+
+### With OpenAI Library
+
+**You can use the Interference API with the OpenAI Python library by changing the `base_url`:**
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="",
+    base_url="http://localhost:1337/v1"
+)
+
+response = client.chat.completions.create(
+    model="gpt-4o-mini",
+    messages=[{"role": "user", "content": "Write a poem about a tree"}],
+    stream=True,
+)
+
+if isinstance(response, dict):
+    # Not streaming
+    print(response.choices[0].message.content)
+else:
+    # Streaming
+    for token in response:
+        content = token.choices[0].delta.content
+        if content is not None:
+            print(content, end="", flush=True)
+
+```
+  
+
+### With Requests Library
+
+**You can also send requests directly to the Interference API using the `requests` library:**
+```python
+import requests
+
+url = "http://localhost:1337/v1/chat/completions"
+
+body = {
+    "model": "gpt-4o-mini",
+    "stream": False,
+    "messages": [
+        {"role": "assistant", "content": "What can you do?"}
+    ]
+}
+
+json_response = requests.post(url, json=body).json().get('choices', [])
+
+for choice in json_response:
+    print(choice.get('message', {}).get('content', ''))
+
+```
+
+## Key Points
+   - The Interference API translates OpenAI API requests into G4F provider requests.
+   - It can be run from either the PyPI package or the cloned repository.
+   - The API supports usage with the OpenAI Python library by changing the `base_url`.
+   - Direct requests can be sent to the API endpoints using libraries like `requests`.
+   - Both text and image generation are supported.
+
+  
+## Conclusion
+The G4F Interference API provides a seamless way to integrate G4F with existing OpenAI-based applications and tools. By following this guide, you should now be able to set up, run, and use the Interference API effectively. Whether you're using it for text generation, image creation, or as a drop-in replacement for OpenAI in your projects, the Interference API offers flexibility and power for your AI-driven applications.
+ 
+
+---
+
+[Return to Home](/)

docs/legacy.md

@@ -0,0 +1,200 @@
+### G4F - Legacy API
+
+#### ChatCompletion
+
+```python
+import g4f
+
+g4f.debug.logging = True  # Enable debug logging
+g4f.debug.version_check = False  # Disable automatic version checking
+print(g4f.Provider.Bing.params)  # Print supported args for Bing
+
+# Using automatic a provider for the given model
+## Streamed completion
+response = g4f.ChatCompletion.create(
+    model="gpt-3.5-turbo",
+    messages=[{"role": "user", "content": "Hello"}],
+    stream=True,
+)
+for message in response:
+    print(message, flush=True, end='')
+
+## Normal response
+response = g4f.ChatCompletion.create(
+    model=g4f.models.gpt_4,
+    messages=[{"role": "user", "content": "Hello"}],
+)  # Alternative model setting
+
+print(response)
+```
+
+##### Completion
+
+```python
+import g4f
+
+allowed_models = [
+    'code-davinci-002',
+    'text-ada-001',
+    'text-babbage-001',
+    'text-curie-001',
+    'text-davinci-002',
+    'text-davinci-003'
+]
+
+response = g4f.Completion.create(
+    model='text-davinci-003',
+    prompt='say this is a test'
+)
+
+print(response)
+```
+
+##### Providers
+
+```python
+import g4f
+
+# Print all available providers
+print([
+    provider.__name__
+    for provider in g4f.Provider.__providers__
+    if provider.working
+])
+
+# Execute with a specific provider
+response = g4f.ChatCompletion.create(
+    model="gpt-3.5-turbo",
+    provider=g4f.Provider.Aichat,
+    messages=[{"role": "user", "content": "Hello"}],
+    stream=True,
+)
+for message in response:
+    print(message)
+```
+
+
+##### Image Upload & Generation
+
+Image upload and generation are supported by three main providers:
+
+- **Bing & Other GPT-4 Providers:** Utilizes Microsoft's Image Creator.
+- **Google Gemini:** Available for free accounts with IP addresses outside Europe.
+- **OpenaiChat with GPT-4:** Accessible for users with a Plus subscription.
+
+```python
+import g4f
+
+# Setting up the request for image creation
+response = g4f.ChatCompletion.create(
+    model=g4f.models.default, # Using the default model
+    provider=g4f.Provider.Gemini, # Specifying the provider as Gemini
+    messages=[{"role": "user", "content": "Create an image like this"}],
+    image=open("images/g4f.png", "rb"), # Image input can be a data URI, bytes, PIL Image, or IO object
+    image_name="g4f.png" # Optional: specifying the filename
+)
+
+# Displaying the response
+print(response)
+
+from g4f.image import ImageResponse
+
+# Get image links from response
+for chunk in g4f.ChatCompletion.create(
+    model=g4f.models.default, # Using the default model
+    provider=g4f.Provider.OpenaiChat, # Specifying the provider as OpenaiChat
+    messages=[{"role": "user", "content": "Create images with dogs"}],
+    access_token="...", # Need a access token from a plus user
+    stream=True,
+    ignore_stream=True
+):
+    if isinstance(chunk, ImageResponse):
+        print(chunk.images) # Print generated image links
+        print(chunk.alt) # Print used prompt for image generation
+```
+
+##### Using Browser
+
+Some providers using a browser to bypass the bot protection. They using the selenium webdriver to control the browser. The browser settings and the login data are saved in a custom directory. If the headless mode is enabled, the browser windows are loaded invisibly. For performance reasons, it is recommended to reuse the browser instances and close them yourself at the end:
+
+```python
+import g4f
+from undetected_chromedriver import Chrome, ChromeOptions
+from g4f.Provider import (
+    Bard,
+    Poe,
+    AItianhuSpace,
+    MyShell,
+    PerplexityAi,
+)
+
+options = ChromeOptions()
+options.add_argument("--incognito");
+webdriver = Chrome(options=options, headless=True)
+for idx in range(10):
+    response = g4f.ChatCompletion.create(
+        model=g4f.models.default,
+        provider=g4f.Provider.MyShell,
+        messages=[{"role": "user", "content": "Suggest me a name."}],
+        webdriver=webdriver
+    )
+    print(f"{idx}:", response)
+webdriver.quit()
+```
+
+##### Async Support
+
+To enhance speed and overall performance, execute providers asynchronously. The total execution time will be determined by the duration of the slowest provider's execution.
+
+```python
+import g4f
+import asyncio
+
+_providers = [
+    g4f.Provider.Aichat,
+    g4f.Provider.ChatBase,
+    g4f.Provider.Bing,
+    g4f.Provider.GptGo,
+    g4f.Provider.You,
+    g4f.Provider.Yqcloud,
+]
+
+async def run_provider(provider: g4f.Provider.BaseProvider):
+    try:
+        response = await g4f.ChatCompletion.create_async(
+            model=g4f.models.default,
+            messages=[{"role": "user", "content": "Hello"}],
+            provider=provider,
+        )
+        print(f"{provider.__name__}:", response)
+    except Exception as e:
+        print(f"{provider.__name__}:", e)
+        
+async def run_all():
+    calls = [
+        run_provider(provider) for provider in _providers
+    ]
+    await asyncio.gather(*calls)
+
+asyncio.run(run_all())
+```
+
+##### Proxy and Timeout Support
+
+All providers support specifying a proxy and increasing timeout in the create functions.
+
+```python
+import g4f
+
+response = g4f.ChatCompletion.create(
+    model=g4f.models.default,
+    messages=[{"role": "user", "content": "Hello"}],
+    proxy="http://host:port",
+    # or socks5://user:pass@host:port
+    timeout=120,  # in secs
+)
+
+print(f"Result:", response)
+```
+
+[Return to Home](/)

docs/local.md

@@ -0,0 +1,164 @@
+
+### G4F - Local Usage Guide
+ 
+
+### Table of Contents
+1. [Introduction](#introduction)
+2. [Required Dependencies](#required-dependencies)
+3. [Basic Usage Example](#basic-usage-example)
+4. [Supported Models](#supported-models)
+5. [Performance Considerations](#performance-considerations)
+6. [Troubleshooting](#troubleshooting)
+
+#### Introduction
+This guide explains how to use g4f to run language models locally. G4F (GPT4Free) allows you to interact with various language models on your local machine, providing a flexible and private solution for natural language processing tasks.
+
+## Usage
+ 
+#### Local inference
+How to use g4f to run language models locally
+  
+#### Required dependencies
+**Make sure to install the required dependencies by running:**
+```bash
+pip install g4f[local]
+```
+or
+```bash
+pip install -U gpt4all
+```
+
+  
+
+#### Basic usage example 
+```python
+from g4f.local import LocalClient
+
+client   = LocalClient()
+response = client.chat.completions.create(
+    model    = 'orca-mini-3b',
+    messages = [{"role": "user", "content": "hi"}],
+    stream   = True
+)
+
+for token in response:
+    print(token.choices[0].delta.content or "")
+```
+
+Upon first use, there will be a prompt asking you if you wish to download the model. If you respond with `y`, g4f will go ahead and download the model for you.
+
+You can also manually place supported models into `./g4f/local/models/`
+  
+
+**You can get a list of the current supported models by running:**
+```python
+from g4f.local import LocalClient
+
+client   = LocalClient()
+client.list_models()
+``` 
+
+```json
+{
+    "mistral-7b": {
+        "path": "mistral-7b-openorca.gguf2.Q4_0.gguf",
+        "ram": "8",
+        "prompt": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n",
+        "system": "<|im_start|>system\nYou are MistralOrca, a large language model trained by Alignment Lab AI. For multi-step problems, write out your reasoning for each step.\n<|im_end|>"
+    },
+    "mistral-7b-instruct": {
+        "path": "mistral-7b-instruct-v0.1.Q4_0.gguf",
+        "ram": "8",
+        "prompt": "[INST] %1 [/INST]",
+        "system": None
+    },
+    "gpt4all-falcon": {
+        "path": "gpt4all-falcon-newbpe-q4_0.gguf",
+        "ram": "8",
+        "prompt": "### Instruction:\n%1\n### Response:\n",
+        "system": None
+    },
+    "orca-2": {
+        "path": "orca-2-13b.Q4_0.gguf",
+        "ram": "16",
+        "prompt": None,
+        "system": None
+    },
+    "wizardlm-13b": {
+        "path": "wizardlm-13b-v1.2.Q4_0.gguf",
+        "ram": "16",
+        "prompt": None,
+        "system": None
+    },
+    "nous-hermes-llama2": {
+        "path": "nous-hermes-llama2-13b.Q4_0.gguf",
+        "ram": "16",
+        "prompt": "### Instruction:\n%1\n### Response:\n",
+        "system": None
+    },
+    "gpt4all-13b-snoozy": {
+        "path": "gpt4all-13b-snoozy-q4_0.gguf",
+        "ram": "16",
+        "prompt": None,
+        "system": None
+    },
+    "mpt-7b-chat": {
+        "path": "mpt-7b-chat-newbpe-q4_0.gguf",
+        "ram": "8",
+        "prompt": "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n",
+        "system": "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>"
+    },
+    "orca-mini-3b": {
+        "path": "orca-mini-3b-gguf2-q4_0.gguf",
+        "ram": "4",
+        "prompt": "### User:\n%1\n### Response:\n",
+        "system": "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
+    },
+    "replit-code-3b": {
+        "path": "replit-code-v1_5-3b-newbpe-q4_0.gguf",
+        "ram": "4",
+        "prompt": "%1",
+        "system": None
+    },
+    "starcoder": {
+        "path": "starcoder-newbpe-q4_0.gguf",
+        "ram": "4",
+        "prompt": "%1",
+        "system": None
+    },
+    "rift-coder-7b": {
+        "path": "rift-coder-v0-7b-q4_0.gguf",
+        "ram": "8",
+        "prompt": "%1",
+        "system": None
+    },
+    "all-MiniLM-L6-v2": {
+        "path": "all-MiniLM-L6-v2-f16.gguf",
+        "ram": "1",
+        "prompt": None,
+        "system": None
+    },
+    "mistral-7b-german": {
+        "path": "em_german_mistral_v01.Q4_0.gguf",
+        "ram": "8",
+        "prompt": "USER: %1 ASSISTANT: ",
+        "system": "Du bist ein hilfreicher Assistent. "
+    }
+}
+```
+
+#### Performance Considerations
+**When running language models locally, consider the following:**
+   - RAM requirements vary by model size (see the 'ram' field in the model list).
+   - CPU/GPU capabilities affect inference speed.
+   - Disk space is needed to store the model files.
+
+#### Troubleshooting
+**Common issues and solutions:**
+   1. **Model download fails**: Check your internet connection and try again.
+   2. **Out of memory error**: Choose a smaller model or increase your system's RAM.
+   3. **Slow inference**: Consider using a GPU or a more powerful CPU.
+
+
+
+[Return to Home](/)

docs/providers-and-models.md

@@ -0,0 +1,214 @@
+
+
+# G4F - Providers and Models
+
+This document provides an overview of various AI providers and models, including text generation, image generation, and vision capabilities. It aims to help users navigate the diverse landscape of AI services and choose the most suitable option for their needs.
+
+## Table of Contents
+  - [Providers](#providers)
+  - [Models](#models)
+    - [Text Models](#text-models)
+    - [Image Models](#image-models)
+    - [Vision Models](#vision-models)
+       - [Providers and vision models](#providers-and-vision-models)
+  - [Conclusion and Usage Tips](#conclusion-and-usage-tips)
+
+---
+## Providers
+| Provider | Text Models | Image Models | Vision Models | Stream | Status | Auth |
+|----------|-------------|--------------|---------------|--------|--------|------|
+|[ai4chat.co](https://www.ai4chat.co)|`g4f.Provider.Ai4Chat`|`gpt-4`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[aichatfree.info](https://aichatfree.info)|`g4f.Provider.AIChatFree`|`gemini-pro`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[api.airforce](https://api.airforce)|`g4f.Provider.Airforce`|`gpt-4o, gpt-4o-mini, gpt-4-turbo, llama-2-7b, llama-3.1-8b, llama-3.1-70b, hermes-2-pro, hermes-2-dpo, phi-2, deepseek-coder, openchat-3.5, openhermes-2.5, lfm-40b, german-7b, zephyr-7b, neural-7b`|`flux, flux-realism', flux-anime, flux-3d, flux-disney, flux-pixel, flux-4o, any-dark, sdxl`|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[aiuncensored.info](https://www.aiuncensored.info)|`g4f.Provider.AIUncensored`|✔|✔|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[allyfy.chat](https://allyfy.chat/)|`g4f.Provider.Allyfy`|`gpt-3.5-turbo`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[bing.com](https://bing.com/chat)|`g4f.Provider.Bing`|`gpt-4`|✔|`gpt-4-vision`|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌+✔|
+|[bing.com/images](https://www.bing.com/images/create)|`g4f.Provider.BingCreateImages`|`❌|✔|❌|❌|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[blackbox.ai](https://www.blackbox.ai)|`g4f.Provider.Blackbox`|`blackboxai, blackboxai-pro, gemini-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gpt-4o, gemini-pro, claude-3.5-sonnet`|`flux`|`blackboxai, gemini-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gpt-4o, gemini-pro`|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[chatgot.one](https://www.chatgot.one/)|`g4f.Provider.ChatGot`|`gemini-pro`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[chatgpt.com](https://chatgpt.com)|`g4f.Provider.ChatGpt`|`?`|`?`|`?`|?|![Unknown](https://img.shields.io/badge/Unknown-grey) |❌|
+|[chatgpt.es](https://chatgpt.es)|`g4f.Provider.ChatGptEs`|`gpt-4o, gpt-4o-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[playground.ai.cloudflare.com](https://playground.ai.cloudflare.com)|`g4f.Provider.Cloudflare`|`gemma-7b, llama-2-7b, llama-3-8b, llama-3.1-8b, llama-3.2-1b, phi-2, qwen-1.5-0-5b, qwen-1.5-8b, qwen-1.5-14b, qwen-1.5-7b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[darkai.foundation/chat](https://darkai.foundation/chat)|`g4f.Provider.DarkAI`|`gpt-4o, gpt-3.5-turbo, llama-3-70b, llama-3-405b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[duckduckgo.com](https://duckduckgo.com/duckchat/v1/chat)|`g4f.Provider.DDG`|`gpt-4o-mini, claude-3-haiku, llama-3.1-70b, mixtral-8x7b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[deepinfra.com](https://deepinfra.com)|`g4f.Provider.DeepInfra`|✔|❌|❌|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[deepinfra.com/chat](https://deepinfra.com/chat)|`g4f.Provider.DeepInfraChat`|`llama-3.1-8b, llama-3.1-70b, wizardlm-2-8x22b, qwen-2-72b`|❌|❌|❌|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[deepinfra.com](https://deepinfra.com)|`g4f.Provider.DeepInfraImage`|❌|✔|❌|❌|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[chat10.free2gpt.xyz](chat10.free2gpt.xyz)|`g4f.Provider.Free2GPT`|`mixtral-7b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|`g4f.Provider.FreeGpt`|`gemini-pro`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[gemini.google.com](https://gemini.google.com)|`g4f.Provider.Gemini`|✔|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[ai.google.dev](https://ai.google.dev)|`g4f.Provider.GeminiPro`|✔|❌|✔|?|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[app.giz.ai](https://app.giz.ai/assistant/)|`g4f.Provider.GizAI`|`gemini-flash`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[developers.sber.ru](https://developers.sber.ru/gigachat)|`g4f.Provider.GigaChat`|✔|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[console.groq.com/playground](https://console.groq.com/playground)|`g4f.Provider.Groq`|✔|❌|❌|?|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[huggingface.co/chat](https://huggingface.co/chat)|`g4f.Provider.HuggingChat`|`llama-3.1-70b, command-r-plus, qwen-2-72b, llama-3.2-11b, hermes-3, mistral-nemo, phi-3.5-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[huggingface.co](https://huggingface.co/chat)|`g4f.Provider.HuggingFace`|✔|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[liaobots.work](https://liaobots.work)|`g4f.Provider.Liaobots`|`gpt-3.5-turbo, gpt-4o-mini, gpt-4o, gpt-4-turbo, grok-2, grok-2-mini, claude-3-opus, claude-3-sonnet, claude-3-5-sonnet, claude-3-haiku, claude-2.1, gemini-flash, gemini-pro`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[magickpen.com](https://magickpen.com)|`g4f.Provider.MagickPen`|`gpt-4o-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[meta.ai](https://www.meta.ai)|`g4f.Provider.MetaAI`|✔|✔|?|?|![Active](https://img.shields.io/badge/Active-brightgreen)|✔|
+|[platform.openai.com](https://platform.openai.com/)|`g4f.Provider.Openai`|✔|❌|✔||![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[chatgpt.com](https://chatgpt.com/)|`g4f.Provider.OpenaiChat`|`gpt-4o, gpt-4o-mini, gpt-4`|❌|✔||![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[www.perplexity.ai)](https://www.perplexity.ai)|`g4f.Provider.PerplexityAi`|✔|❌|❌|?|![Disabled](https://img.shields.io/badge/Disabled-red)|❌|
+|[perplexity.ai](https://www.perplexity.ai)|`g4f.Provider.PerplexityApi`|✔|❌|❌|?|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[labs.perplexity.ai](https://labs.perplexity.ai)|`g4f.Provider.PerplexityLabs`|`sonar-online, sonar-chat, llama-3.1-8b, llama-3.1-70b`|❌|❌|?|![Cloudflare](https://img.shields.io/badge/Cloudflare-f48d37)|❌|
+|[pi.ai/talk](https://pi.ai/talk)|`g4f.Provider.Pi`|`pi`|❌|❌|?|![Unknown](https://img.shields.io/badge/Unknown-grey)|❌|
+|[]()|`g4f.Provider.Pizzagpt`|`gpt-4o-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[poe.com](https://poe.com)|`g4f.Provider.Poe`|✔|❌|❌|?|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[app.prodia.com](https://app.prodia.com)|`g4f.Provider.Prodia`|❌|✔|❌|❌|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[raycast.com](https://raycast.com)|`g4f.Provider.Raycast`|✔|❌|❌|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[chat.reka.ai](https://chat.reka.ai/)|`g4f.Provider.Reka`|✔|❌|✔|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[replicate.com](https://replicate.com)|`g4f.Provider.Replicate`|✔|❌|❌|?|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[replicate.com](https://replicate.com)|`g4f.Provider.ReplicateHome`|`gemma-2b, llava-13b`|`sd-3, sdxl, playground-v2.5`|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[replicate.com](https://replicate.com)|`g4f.Provider.RubiksAI`|`llama-3.1-70b, gpt-4o-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[talkai.info](https://talkai.info)|`g4f.Provider.TalkAi`|✔|❌|❌|✔|![Disabled](https://img.shields.io/badge/Disabled-red)|❌|
+|[teach-anything.com](https://www.teach-anything.com)|`g4f.Provider.TeachAnything`|`llama-3.1-70b`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[beta.theb.ai](https://beta.theb.ai)|`g4f.Provider.Theb`|✔|❌|❌|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[beta.theb.ai](https://beta.theb.ai)|`g4f.Provider.ThebApi`|✔|❌|❌|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[console.upstage.ai/playground/chat](https://console.upstage.ai/playground/chat)|`g4f.Provider.Upstage`|`solar-pro, solar-mini`|❌|❌|✔|![Active](https://img.shields.io/badge/Active-brightgreen)|❌|
+|[whiterabbitneo.com](https://www.whiterabbitneo.com)|`g4f.Provider.WhiteRabbitNeo`|✔|❌|❌|?|![Unknown](https://img.shields.io/badge/Unknown-grey)|✔|
+|[you.com](https://you.com)|`g4f.Provider.You`|✔|✔|✔|✔|![Unknown](https://img.shields.io/badge/Unknown-grey)|❌+✔|
+
+## Models
+
+### Text Models
+| Model | Base Provider | Providers | Website |
+|-------|---------------|-----------|---------|
+|gpt-3.5-turbo|OpenAI|4+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-3-5-turbo)|
+|gpt-4|OpenAI|6+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|
+|gpt-4-turbo|OpenAI|4+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4)|
+|gpt-4o|OpenAI|7+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o)|
+|gpt-4o-mini|OpenAI|10+ Providers|[platform.openai.com](https://platform.openai.com/docs/models/gpt-4o-mini)|
+|o1|OpenAI|0+ Providers|[platform.openai.com](https://openai.com/index/introducing-openai-o1-preview/)|
+|o1-mini|OpenAI|0+ Providers|[platform.openai.com](https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning/)|
+|llama-2-7b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-2-7b)|
+|llama-2-13b|Meta Llama|1+ Providers|[llama.com](https://www.llama.com/llama2/)|
+|llama-3-8b|Meta Llama|4+ Providers|[ai.meta.com](https://ai.meta.com/blog/meta-llama-3/)|
+|llama-3-70b|Meta Llama|4+ Providers|[ai.meta.com](https://ai.meta.com/blog/meta-llama-3/)|
+|llama-3.1-8b|Meta Llama|7+ Providers|[ai.meta.com](https://ai.meta.com/blog/meta-llama-3-1/)|
+|llama-3.1-70b|Meta Llama|14+ Providers|[ai.meta.com](https://ai.meta.com/blog/meta-llama-3-1/)|
+|llama-3.1-405b|Meta Llama|5+ Providers|[ai.meta.com](https://ai.meta.com/blog/meta-llama-3-1/)|
+|llama-3.2-1b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Llama-3.2-1B)|
+|llama-3.2-3b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/blog/llama32)|
+|llama-3.2-11b|Meta Llama|3+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)|
+|llama-3.2-90b|Meta Llama|2+ Providers|[ai.meta.com](https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/)|
+|llamaguard-7b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/LlamaGuard-7b)|
+|llamaguard-2-8b|Meta Llama|1+ Providers|[huggingface.co](https://huggingface.co/meta-llama/Meta-Llama-Guard-2-8B)|
+|mistral-7b|Mistral AI|4+ Providers|[mistral.ai](https://mistral.ai/news/announcing-mistral-7b/)|
+|mixtral-8x7b|Mistral AI|6+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-of-experts/)|
+|mixtral-8x22b|Mistral AI|3+ Providers|[mistral.ai](https://mistral.ai/news/mixtral-8x22b/)|
+|mistral-nemo|Mistral AI|2+ Providers|[huggingface.co](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)|
+|mistral-large|Mistral AI|2+ Providers|[mistral.ai](https://mistral.ai/news/mistral-large-2407/)|
+|mixtral-8x7b-dpo|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|
+|hermes-2-dpo|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)|
+|hermes-2|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B)|
+|yi-34b|NousResearch|1+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B)|
+|hermes-3|NousResearch|2+ Providers|[huggingface.co](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B)|
+|gemini|Google DeepMind|1+ Providers|[deepmind.google](http://deepmind.google/technologies/gemini/)|
+|gemini-flash|Google DeepMind|4+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/flash/)|
+|gemini-pro|Google DeepMind|10+ Providers|[deepmind.google](https://deepmind.google/technologies/gemini/pro/)|
+|gemma-2b|Google|5+ Providers|[huggingface.co](https://huggingface.co/google/gemma-2b)|
+|gemma-2b-9b|Google|1+ Providers|[huggingface.co](https://huggingface.co/google/gemma-2-9b)|
+|gemma-2b-27b|Google|2+ Providers|[huggingface.co](https://huggingface.co/google/gemma-2-27b)|
+|gemma-7b|Google|1+ Providers|[huggingface.co](https://huggingface.co/google/gemma-7b)|
+|gemma_2_27b|Google|1+ Providers|[huggingface.co](https://huggingface.co/blog/gemma2)|
+|claude-2.1|Anthropic|1+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-2)|
+|claude-3-haiku|Anthropic|4+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-3-haiku)|
+|claude-3-sonnet|Anthropic|2+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-3-family)|
+|claude-3-opus|Anthropic|2+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-3-family)|
+|claude-3.5-sonnet|Anthropic|6+ Providers|[anthropic.com](https://www.anthropic.com/news/claude-3-5-sonnet)|
+|blackboxai|Blackbox AI|1+ Providers|[docs.blackbox.chat](https://docs.blackbox.chat/blackbox-ai-1)|
+|blackboxai-pro|Blackbox AI|1+ Providers|[docs.blackbox.chat](https://docs.blackbox.chat/blackbox-ai-1)|
+|yi-1.5-9b|01-ai|1+ Providers|[huggingface.co](https://huggingface.co/01-ai/Yi-1.5-9B)|
+|phi-2|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/phi-2)|
+|phi-3-medium-4k|Microsoft|1+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct)|
+|phi-3.5-mini|Microsoft|2+ Providers|[huggingface.co](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct)|
+|dbrx-instruct|Databricks|1+ Providers|[huggingface.co](https://huggingface.co/databricks/dbrx-instruct)|
+|command-r-plus|CohereForAI|1+ Providers|[docs.cohere.com](https://docs.cohere.com/docs/command-r-plus)|
+|sparkdesk-v1.1|iFlytek|1+ Providers|[xfyun.cn](https://www.xfyun.cn/doc/spark/Guide.html)|
+|qwen|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen)|
+|qwen-1.5-0.5b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-0.5B)|
+|qwen-1.5-7b|Qwen|2+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-7B)|
+|qwen-1.5-14b|Qwen|3+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-14B)|
+|qwen-1.5-72b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-72B)|
+|qwen-1.5-110b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-110B)|
+|qwen-1.5-1.8b|Qwen|1+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen1.5-1.8B)|
+|qwen-2-72b|Qwen|4+ Providers|[huggingface.co](https://huggingface.co/Qwen/Qwen2-72B)|
+|glm-3-6b|Zhipu AI|1+ Providers|[github.com/THUDM/ChatGLM3](https://github.com/THUDM/ChatGLM3)|
+|glm-4-9B|Zhipu AI|1+ Providers|[github.com/THUDM/GLM-4](https://github.com/THUDM/GLM-4)|
+|solar-1-mini|Upstage|1+ Providers|[upstage.ai/](https://www.upstage.ai/feed/product/solarmini-performance-report)|
+|solar-10-7b|Upstage|1+ Providers|[huggingface.co](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0)|
+|solar-pro|Upstage|1+ Providers|[huggingface.co](https://huggingface.co/upstage/solar-pro-preview-instruct)|
+|pi|Inflection|1+ Providers|[inflection.ai](https://inflection.ai/blog/inflection-2-5)|
+|deepseek-coder|DeepSeek|1+ Providers|[huggingface.co](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct)|
+|wizardlm-2-7b|WizardLM|1+ Providers|[huggingface.co](https://huggingface.co/dreamgen/WizardLM-2-7B)|
+|wizardlm-2-8x22b|WizardLM|2+ Providers|[huggingface.co](https://huggingface.co/alpindale/WizardLM-2-8x22B)|
+|sh-n-7b|Together|1+ Providers|[huggingface.co](https://huggingface.co/togethercomputer/StripedHyena-Nous-7B)|
+|llava-13b|Yorickvp|1+ Providers|[huggingface.co](https://huggingface.co/liuhaotian/llava-v1.5-13b)|
+|lzlv-70b|Lzlv|1+ Providers|[huggingface.co](https://huggingface.co/lizpreciatior/lzlv_70b_fp16_hf)|
+|openchat-3.5|OpenChat|1+ Providers|[huggingface.co](https://huggingface.co/openchat/openchat_3.5)|
+|openchat-3.6-8b|OpenChat|1+ Providers|[huggingface.co](https://huggingface.co/openchat/openchat-3.6-8b-20240522)|
+|phind-codellama-34b-v2|Phind|1+ Providers|[huggingface.co](https://huggingface.co/Phind/Phind-CodeLlama-34B-v2)|
+|dolphin-2.9.1-llama-3-70b|Cognitive Computations|1+ Providers|[huggingface.co](https://huggingface.co/cognitivecomputations/dolphin-2.9.1-llama-3-70b)|
+|grok-2-mini|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-2)|
+|grok-2|x.ai|1+ Providers|[x.ai](https://x.ai/blog/grok-2)|
+|sonar-online|Perplexity AI|2+ Providers|[docs.perplexity.ai](https://docs.perplexity.ai/)|
+|sonar-chat|Perplexity AI|1+ Providers|[docs.perplexity.ai](https://docs.perplexity.ai/)|
+|mythomax-l2-13b|Gryphe|1+ Providers|[huggingface.co](https://huggingface.co/Gryphe/MythoMax-L2-13b)|
+|cosmosrp|Gryphe|1+ Providers|[huggingface.co](https://huggingface.co/PawanKrd/CosmosRP-8k)|
+|german-7b|TheBloke|1+ Providers|[huggingface.co](https://huggingface.co/TheBloke/DiscoLM_German_7b_v1-GGUF)|
+|tinyllama-1.1b|TinyLlama|1+ Providers|[huggingface.co](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)|
+|cybertron-7b|TheBloke|1+ Providers|[huggingface.co](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16)|
+|openhermes-2.5|Teknium|1+ Providers|[huggingface.co](https://huggingface.co/datasets/teknium/OpenHermes-2.5)|
+|lfm-40b|Liquid|1+ Providers|[liquid.ai](https://www.liquid.ai/liquid-foundation-models)|
+|zephyr-7b|HuggingFaceH4|1+ Providers|[huggingface.co](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)|
+
+
+### Image Models
+| Model | Base Provider | Providers | Website |
+|-------|---------------|-----------|---------|
+|sdxl|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/docs/diffusers/en/using-diffusers/sdxl)|
+|sdxl-lora|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/blog/lcm_lora)|
+|sdxl-turbo|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/stabilityai/sdxl-turbo)|
+|sd-1.5|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/runwayml/stable-diffusion-v1-5)|
+|sd-3|Stability AI|1+ Providers|[huggingface.co](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_3)|
+|playground-v2.5|Playground AI|1+ Providers|[huggingface.co](https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic)|
+|flux|Black Forest Labs|2+ Providers|[github.com/black-forest-labs/flux](https://github.com/black-forest-labs/flux)|
+|flux-pro|Black Forest Labs|2+ Providers|[github.com/black-forest-labs/flux](https://github.com/black-forest-labs/flux)|
+|flux-realism|Flux AI|2+ Providers|[]()|
+|flux-anime|Flux AI|1+ Providers|[]()|
+|flux-3d|Flux AI|1+ Providers|[]()|
+|flux-disney|Flux AI|1+ Providers|[]()|
+|flux-pixel|Flux AI|1+ Providers|[]()|
+|flux-4o|Flux AI|1+ Providers|[]()|
+|flux-schnell|Black Forest Labs|2+ Providers|[huggingface.co](https://huggingface.co/black-forest-labs/FLUX.1-schnell)|
+|dalle|OpenAI|1+ Providers|[openai.com](https://openai.com/index/dall-e/)|
+|dalle-2|OpenAI|1+ Providers|[openai.com](https://openai.com/index/dall-e-2/)|
+|emi||1+ Providers|[]()|
+|any-dark||1+ Providers|[]()|
+|midjourney|Midjourney|1+ Providers|[docs.midjourney.com](https://docs.midjourney.com/docs/model-versions)|
+
+### Vision Models
+| Model | Base Provider | Providers | Website |
+|-------|---------------|-----------|---------|
+|gpt-4-vision|OpenAI|1+ Providers|[openai.com](https://openai.com/research/gpt-4v-system-card)|
+|gemini-pro-vision|Google DeepMind|1+ Providers | [deepmind.google](https://deepmind.google/technologies/gemini/)|
+|blackboxai|Blackbox AI|1+ Providers|[docs.blackbox.chat](https://docs.blackbox.chat/blackbox-ai-1)|
+
+### Providers and vision models
+| Provider | Base Provider | | Vision Models | Status | Auth |
+|-------|---------------|-----------|---------|---------|---------|
+| `g4f.Provider.Blackbox` | Blackbox AI | | `blackboxai, gemini-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gpt-4o, gemini-pro` | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
+
+## Conclusion and Usage Tips
+This document provides a comprehensive overview of various AI providers and models available for text generation, image generation, and vision tasks. **When choosing a provider or model, consider the following factors:**
+   1. **Availability**: Check the status of the provider to ensure it's currently active and accessible.
+   2. **Model Capabilities**: Different models excel at different tasks. Choose a model that best fits your specific needs, whether it's text generation, image creation, or vision-related tasks.
+   3. **Authentication**: Some providers require authentication, while others don't. Consider this when selecting a provider for your project.
+   4. **Streaming Support**: If real-time responses are important for your application, prioritize providers that offer streaming capabilities.
+   5. **Vision Models**: For tasks requiring image understanding or multimodal interactions, look for providers offering vision models.
+
+Remember to stay updated with the latest developments in the AI field, as new models and providers are constantly emerging and evolving.
+
+---
+
+[Return to Home](/)

docs/requirements.md

@@ -0,0 +1,47 @@
+### G4F - Additional Requirements
+
+#### Introduction
+
+You can install requirements partially or completely. So G4F can be used as you wish. You have the following options for this:
+
+#### Options
+
+Install g4f with all possible dependencies:
+```
+pip install -U g4f[all]
+```
+Or install only g4f and the required packages for the OpenaiChat provider:
+```
+pip install -U g4f[openai]
+```
+Install required packages for the Interference API:
+```
+pip install -U g4f[api]
+```
+Install required packages for the Web UI:
+```
+pip install -U g4f[gui]
+```
+Install required packages for uploading / generating images:
+```
+pip install -U g4f[image]
+```
+Install required packages for using the webdriver:
+```
+pip install -U g4f[webdriver]
+```
+Install required package for proxy support with aiohttp:
+```
+pip install -U aiohttp_socks
+```
+Install required package for loading cookies from browser:
+```
+pip install browser_cookie3
+```
+Install all packages and uninstall this package for disabling the webdriver:
+```
+pip uninstall undetected-chromedriver
+```
+
+---
+[Return to Home](/)

docs/webview.md

@@ -0,0 +1,30 @@
+### G4F - Webview GUI
+
+Open the GUI in a window of your OS. Runs on a local/static/ssl server and use a JavaScript API.
+Supports login into the OpenAI Chat (.har files), Image Upload and streamed Text Generation.
+
+Supports all platforms, but only Linux/Windows tested.
+
+1. Install all python requirements with:
+
+```bash
+pip install g4f[webview]
+```
+
+2. *a)* Follow the **OS specific** steps here:
+ [pywebview installation](https://pywebview.flowrl.com/guide/installation.html#dependencies)
+
+2. *b)* **WebView2** on **Windows**: Our application requires the *WebView2 Runtime* to be installed on your system. If you do not have it installed, please download and install it from the [Microsoft Developer Website](https://developer.microsoft.com/en-us/microsoft-edge/webview2/). If you already have *WebView2 Runtime* installed but are encountering issues, navigate to *Installed Windows Apps*, select *WebView2*, and opt for the repair option.
+
+3. Run the app with:
+
+```python
+from g4f.gui.webview import run_webview
+run_webview(debug=True)
+```
+or execute the following command:
+```bash
+python -m g4f.gui.webview -debug
+```
+
+[Return to Home](/)

etc/examples/api.py

@@ -0,0 +1,51 @@
+import requests
+import json
+import uuid
+
+url = "http://localhost:1337/v1/chat/completions"
+conversation_id = str(uuid.uuid4())
+body = {
+    "model": "",
+    "provider": "Copilot",
+    "stream": True,
+    "messages": [
+        {"role": "user", "content": "Hello, i am Heiner. How are you?"}
+    ],
+    "conversation_id": conversation_id
+}
+response = requests.post(url, json=body, stream=True)
+response.raise_for_status()
+for line in response.iter_lines():
+    if line.startswith(b"data: "):
+        try:
+            json_data = json.loads(line[6:])
+            if json_data.get("error"):
+                print(json_data)
+                break
+            print(json_data.get("choices", [{"delta": {}}])[0]["delta"].get("content", ""), end="")
+        except json.JSONDecodeError:
+            pass
+print()
+print()
+print()
+body = {
+    "model": "",
+    "provider": "Copilot",
+    "stream": True,
+    "messages": [
+        {"role": "user", "content": "Tell me somethings about my name"}
+    ],
+    "conversation_id": conversation_id
+}
+response = requests.post(url, json=body, stream=True)
+response.raise_for_status()
+for line in response.iter_lines():
+    if line.startswith(b"data: "):
+        try:
+            json_data = json.loads(line[6:])
+            if json_data.get("error"):
+                print(json_data)
+                break
+            print(json_data.get("choices", [{"delta": {}}])[0]["delta"].get("content", ""), end="")
+        except json.JSONDecodeError:
+            pass

etc/examples/image_api.py

@@ -0,0 +1,9 @@
+import requests
+url = "http://localhost:1337/v1/images/generations"
+body = {
+    "model": "dall-e",
+    "prompt": "hello world user",
+    #"response_format": "b64_json",
+}
+data = requests.post(url, json=body, stream=True).json()
+print(data)