app added

app.py

@@ -0,0 +1,25 @@
+from langchain.document_loaders import PyPDFDirectoryLoader
+from langchain.vectorstores import Chroma
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain import HuggingFaceHub
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.question_answering import load_qa_chain
+import streamlit as st
+from langchain.chains import RetrievalQA
+
+def main():
+    pdf_folder_path = "./PDFfiles"
+    loader = PyPDFDirectoryLoader(pdf_folder_path)
+    docs = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter (chunk_size=1000, chunk_overlap=200)
+    texts = text_splitter.split_documents(docs)
+    embeddings = HuggingFaceEmbeddings()
+    vectordb = Chroma.from_documents(documents=texts,embedding=embeddings)
+    llm = HuggingFaceHub(repo_id="google/flan-t5-small", model_kwargs={"temperature":0,"max_length":200}, huggingfacehub_api_token="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") # type: ignore
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff",retriever=vectordb.as_retriever(search_type="mmr", search_kwargs={'fetch_k': 30}), return_source_documents=True)
+    query = st.text_input("Ask a question: ")
+    qa(inputs=query,return_only_outputs=True)
+    result = qa({"query": query})
+    st.write(result["result"])
+    st.write(result["source_documents"][0])
+main()

requirements.txt

@@ -0,0 +1,122 @@
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+anyio==3.7.1
+async-timeout==4.0.3
+attrs==23.1.0
+backoff==2.2.1
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+charset-normalizer==3.2.0
+chroma-hnswlib==0.7.2
+chromadb==0.4.5
+click==8.1.6
+colorama==0.4.6
+coloredlogs==15.0.1
+dataclasses-json==0.5.14
+datasets==2.14.4
+decorator==5.1.1
+dill==0.3.7
+distlib==0.3.7
+faiss-cpu==1.7.4
+fastapi==0.99.1
+filelock==3.12.2
+flatbuffers==23.5.26
+frozenlist==1.4.0
+fsspec==2023.6.0
+gitdb==4.0.10
+GitPython==3.1.32
+greenlet==2.0.2
+h11==0.14.0
+httptools==0.6.0
+huggingface-hub==0.16.4
+humanfriendly==10.0
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.0.1
+Jinja2==3.1.2
+joblib==1.3.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+langchain==0.0.261
+langsmith==0.0.20
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.4
+multiprocess==0.70.15
+mypy-extensions==1.0.0
+networkx==3.1
+nltk==3.8.1
+numexpr==2.8.5
+numpy==1.25.2
+onnxruntime==1.15.1
+openapi-schema-pydantic==1.2.4
+overrides==7.4.0
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+pipenv==2023.7.11
+platformdirs==3.10.0
+posthog==3.0.1
+protobuf==4.24.0
+pulsar-client==3.2.0
+pyarrow==12.0.1
+pydantic==1.10.12
+pydeck==0.8.0
+Pygments==2.16.1
+Pympler==1.0.1
+pypdf==3.15.0
+PyPika==0.48.9
+pyreadline3==3.4.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0.1
+referencing==0.30.2
+regex==2023.8.8
+requests==2.31.0
+rich==13.5.2
+rpds-py==0.9.2
+safetensors==0.3.2
+scikit-learn==1.3.0
+scipy==1.11.1
+sentence-transformers==2.2.2
+sentencepiece==0.1.99
+six==1.16.0
+smmap==5.0.0
+sniffio==1.3.0
+SQLAlchemy==2.0.19
+starlette==0.27.0
+streamlit==1.25.0
+sympy==1.12
+tenacity==8.2.2
+threadpoolctl==3.2.0
+tokenizers==0.13.3
+toml==0.10.2
+toolz==0.12.0
+torch==2.0.1
+torchvision==0.15.2
+tornado==6.3.2
+tqdm==4.66.1
+transformers==4.31.0
+typing-inspect==0.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.4
+uvicorn==0.23.2
+validators==0.20.0
+virtualenv==20.24.2
+virtualenv-clone==0.5.7
+watchdog==3.0.0
+watchfiles==0.19.0
+websockets==11.0.3
+xxhash==3.3.0
+yarl==1.9.2
+zipp==3.16.2