Upload 14 files

Search-Your-PDF-App-main/.gitignore

@@ -0,0 +1,160 @@
+# 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
+
+# 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/#use-with-ide
+.pdm.toml
+
+# 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/

Search-Your-PDF-App-main/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 AI Anytime
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Search-Your-PDF-App-main/README.md

@@ -0,0 +1,2 @@
+# Search-Your-PDF-App
+Search Your PDF App using Langchain, ChromaDB, Sentence Transformers, and LaMiNi LM Model. This app is completely powered by Open Source Models.  No OpenAI key is required.

Search-Your-PDF-App-main/app.py

@@ -0,0 +1,76 @@
+import streamlit as st 
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import pipeline
+import torch
+import base64
+import textwrap
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma 
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+from constants import CHROMA_SETTINGS
+
+#model and tokenizer loading
+checkpoint = "LaMini-T5-738M"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+base_model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, device_map='auto', torch_dtype=torch.float32)
+
+@st.cache_resource
+def llm_pipeline():
+    pipe = pipeline(
+        'text2text-generation',
+        model = base_model,
+        tokenizer = tokenizer,
+        max_length = 256,
+        do_sample=True,
+        temperature = 0.3,
+        top_p = 0.95
+    )
+    local_llm = HuggingFacePipeline(pipeline=pipe)
+    return local_llm
+
+@st.cache_resource
+def qa_llm():
+    llm = llm_pipeline()
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = Chroma(persist_directory="db", embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
+    retriever = db.as_retriever()
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
+    return qa
+
+def process_answer(instruction):
+    response = ''
+    instruction = instruction
+    qa = qa_llm()
+    generated_text = qa(instruction)
+    answer = generated_text['result']
+    # metadata = generated_text['metadata']
+    # for text in generated_text:
+        
+    #     print(answer)
+
+    # wrapped_text = textwrap.fill(response, 100)
+    # return wrapped_text
+    return answer,generated_text
+
+def main():
+    st.title("Search Your PDF 🐦📄")
+    with st.expander("About the App"):
+        st.markdown(
+            """
+            This is a Generative AI powered Question and Answering app that responds to questions about your PDF File.
+            """
+        )
+    question = st.text_area("Enter your Question")
+    if st.button("Ask"):
+        st.info("Your Question: " + question)
+
+        st.info("Your Answer")
+        answer, metadata = process_answer(question)
+        st.write(answer)
+        st.write(metadata)
+
+
+if __name__ == '__main__':
+    main()
+

Search-Your-PDF-App-main/constants.py

@@ -0,0 +1,9 @@
+import os 
+from chromadb.config import Settings 
+
+#Define the chroma settings
+CHROMA_SETTINGS = Settings(
+    chroma_db_impl = 'duckdb+parquet',
+    persist_directory = "db",
+    anonymized_telemetry = False
+)

Search-Your-PDF-App-main/db/chroma-collections.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50ad2ffaf7bcd328753a4333a488dc2f354d5c5b664ed15b7e61093c3b45676
+size 557

Search-Your-PDF-App-main/db/chroma-embeddings.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f44cb845a13ba159ff3d4423fcf8f8dc37293a625855e1a7a74ce27adc4972f
+size 37262

Search-Your-PDF-App-main/db/index/id_to_uuid_0ff18d02-2c2d-48fc-a6a8-c763775f8664.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b1e584dd670e5cf77dcfb49222fb0440bbdef5458f3586b2e197c7bcf82fb0
+size 444

Search-Your-PDF-App-main/db/index/index_0ff18d02-2c2d-48fc-a6a8-c763775f8664.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb328603e4c6019ba5abfd6d1f81679e2f9cb9bf912eb2e34e6022a8391f8e9
+size 21936

Search-Your-PDF-App-main/db/index/index_metadata_0ff18d02-2c2d-48fc-a6a8-c763775f8664.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765ce47a48c59b5d5ef9d722a22d88f820ca730b9508407c91a311af65fa9789
+size 103

Search-Your-PDF-App-main/db/index/uuid_to_id_0ff18d02-2c2d-48fc-a6a8-c763775f8664.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa55736b4535834632bb88f75ce4f0773149729cadfbf42b5a7edc4270d1918
+size 497

Search-Your-PDF-App-main/ingest.py

@@ -0,0 +1,28 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma 
+import os 
+from constants import CHROMA_SETTINGS
+
+
+persist_directory = "db"
+
+
+def main():
+    for root, dirs, files in os.walk("docs"):
+        for file in files:
+            if file.endswith(".pdf"):
+                print(file)
+                loader = PDFMinerLoader(os.path.join(root, file))
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+    #create embeddings here
+    embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+    db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
+    db.persist()
+    db=None
+
+if __name__ == "__main__":
+    main()

Search-Your-PDF-App-main/requirements.txt

@@ -0,0 +1,12 @@
+langchain
+streamlit
+transformers
+requests
+torch
+einops
+accelerate
+bitsandbytes
+pdfminer.six
+bs4
+sentence_transformers
+chromadb