initial commit

.gitignore

@@ -0,0 +1,171 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# PyPI configuration file
+.pypirc

app.py

@@ -0,0 +1,85 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+import os
+import logging
+import asyncio
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+api_key = os.getenv("HUGGING_FACE_API_TOKEN")
+
+# Available models
+models = {
+    "Llama-3B": "meta-llama/Llama-3.2-3B-Instruct",
+    "Gemma-7B": "google/gemma-1.1-7b-it",
+    "DeepSeek-Coder": "deepseek-ai/deepseek-coder-1.3b-instruct",
+    "Gemma-27B": "google/gemma-2-27b-it",
+    "DeepSeek-R1": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
+    "Mistral-7B": "mistralai/Mistral-7B-Instruct-v0.3"
+}
+
+# Initialize client
+client = InferenceClient(api_key=api_key)
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Function to interact with selected model
+async def chat_with_model(user_query, model_name):
+    if model_name not in models:
+        return "❌ Invalid model selection. Please choose a valid model."
+
+    model_id = models[model_name]
+    messages = [
+        {"role": "system", "content": 
+        """
+        """
+        },
+        {"role": "user", "content": user_query}
+    ]
+
+    max_retries = 3
+    for attempt in range(1, max_retries + 1):
+        try:
+            response = client.chat.completions.create(
+                model=model_id,
+                messages=messages,
+                temperature=0.5,
+                max_tokens=1024,  # Reduce for faster response
+                top_p=0.7,
+                stream=False
+            )
+
+            return response.choices[0].message.content
+        except Exception as e:
+            logger.warning(f"Attempt {attempt}/{max_retries} failed: {str(e)}")
+            if attempt < max_retries:
+                await asyncio.sleep(1)  # Short delay before retrying
+
+    return "❌ The model is currently unavailable after multiple retries. Please try again later."
+
+# Create Gradio UI
+def chat_interface(user_query, model_name):
+    return asyncio.run(chat_with_model(user_query, model_name))
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Harry's AI Chatbot")
+    gr.Markdown("### Select a model and ask your question to get a response from the AI.")
+    
+    with gr.Row():
+        model_dropdown = gr.Dropdown(
+            choices=list(models.keys()), 
+            label="Select AI Model", 
+            value="Mistral-7B"
+        )
+    
+    user_input = gr.Textbox(label="Enter your message", placeholder="Type your question here...")
+    chat_button = gr.Button("Chat")
+    output_text = gr.Textbox(label="AI Response", interactive=False)
+
+    chat_button.click(chat_interface, inputs=[user_input, model_dropdown], outputs=output_text)
+
+# Launch Gradio app
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+huggingface_hub
+python-dotenv
+uvicorn