Renamed app to rag; created .md file

rauni98iitr · rauni98iitr · commit e7acc09e10ba · 2024-03-29T03:14:28.000+05:30
diff --git a/.gitignore b/.gitignore
@@ -1,2 +1,3 @@
 .venv/
-vector_stores/
+vector_stores/
+__pycache__/
diff --git a/rag.py b/rag.py
@@ -14,8 +14,6 @@
 from langchain_core.runnables import RunnablePassthrough
 from langchain_core.output_parsers import StrOutputParser
 
-from transformers import AutoTokenizer, AutoModelForQuestionAnswering
-from transformers import AutoTokenizer, pipeline
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
 # for streaming in Streamlit without LECL
@@ -61,9 +59,9 @@ def on_llm_new_token(self, token: str, **kwargs) -> None:
 def format_docs(docs):
     return "\n\n".join([doc.page_content for doc in docs])
 
-####################### RAG #################################
-
+############################################## RAG ########################################################
 
+########## Creating prompt ##########
 prompt_template = """Use the following pieces of context regarding titanic ship to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.
 
 {context}
@@ -74,7 +72,7 @@ def format_docs(docs):
 
 prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
 
-#VectorDB creation and saving to disk
+########## VectorDB creation and saving to disk ##########
 client = chromadb.Client()
 
 persist_directory="/Users/raunakanand/Documents/Work_R/llm0/vector_stores"
@@ -86,7 +84,7 @@ def format_docs(docs):
 )
 vectordb.persist()
 
-#VectorDB -loading from disk
+########## VectorDB -loading from disk ##########
 vectordb = Chroma(persist_directory=persist_directory, embedding_function=embeddings, collection_name='chroma1')
 retriever = vectordb.as_retriever(search_kwargs={"k": 3})
 
@@ -107,12 +105,14 @@ def format_docs(docs):
     # callbacks=[StreamingStdOutCallbackHandler()]
 )
 
+########## When using RetrievalQA chain from llm's chain ##########
 qa = RetrievalQA.from_chain_type(llm=llm, chain_type='stuff',
                                  retriever=retriever,
                                 #  return_source_documents=True,
                                  chain_type_kwargs={'prompt': prompt},
                                  verbose=False)
 
+########## RAG's chain in langchain's LECL format ##########
 rag_chain = ({"context": retriever | format_docs, "question": RunnablePassthrough()} | 
              prompt | llm | StrOutputParser())
 
@@ -121,7 +121,6 @@ def inference(query: str):
     # return qa.run(query)
     return rag_chain.stream(query)
 
-print('final')
 
 
 
diff --git a/readme.md b/readme.md
@@ -4,7 +4,35 @@ transformers
 chromadb
 streamlit
 sentence-transformers
-CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python
 # Example: METAL
 CMAKE_ARGS="-DLLAMA_METAL=on"  FORCE_CMAKE=1 pip install llama-cpp-python==0.1.83 --no-cache-dir
-llama_cpp_python
+
+
+
+# Enviornment Setup 
+
+1. Clone the repo using git:
+    ```shell
+    git clone https://github.com/rauni-iitr/langchain_chromaDB_opensourceLLM_streamlit.git
+    ```
+
+2. Create a virtual enviornment, with 'venv' or with 'conda' and activate.
+    ```shell
+    python3 -m venv .venv
+    source .venv/bin/activate
+    ```
+
+3. Now this rag application is built using few dependencies:
+    - pypdf -- for reading pdf documents
+    - chromadb -- vectorDB for creating a vector store
+    - transformers -- dependency for sentence-transfors, atleast in this repository
+    - sentence-transformers -- for embedding models to convert pdf documnts into vectors
+    - streamlit -- to make UI for the LLM PDF's Q&A
+    - llama-cpp_python -- to load gguf files for CPU inference of LLMs
+
+    You can install all of these with pip;
+    ```shell
+    pip install pypdf chromadb transformers sentence-transformers streamlit
+    ```
+    
+ 
diff --git a/requirements.txt b/requirements.txt
@@ -0,0 +1,137 @@
+aiohttp==3.9.3
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.3.0
+asgiref==3.8.1
+attrs==23.2.0
+backoff==2.2.1
+bcrypt==4.1.2
+blinker==1.7.0
+build==1.2.1
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+chroma-hnswlib==0.7.3
+chromadb==0.4.24
+click==8.1.7
+coloredlogs==15.0.1
+dataclasses-json==0.6.4
+Deprecated==1.2.14
+diskcache==5.6.3
+fastapi==0.110.0
+filelock==3.13.3
+flatbuffers==24.3.25
+frozenlist==1.4.1
+fsspec==2024.3.1
+gitdb==4.0.11
+GitPython==3.1.42
+google-auth==2.29.0
+googleapis-common-protos==1.63.0
+grpcio==1.62.1
+h11==0.14.0
+httptools==0.6.1
+huggingface-hub==0.22.1
+humanfriendly==10.0
+idna==3.6
+importlib-metadata==6.11.0
+importlib_resources==6.4.0
+Jinja2==3.1.3
+joblib==1.3.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kubernetes==29.0.0
+langchain==0.1.13
+langchain-community==0.0.29
+langchain-core==0.1.36
+langchain-text-splitters==0.0.1
+langsmith==0.1.36
+llama_cpp_python==0.1.83
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+marshmallow==3.21.1
+mdurl==0.1.2
+mmh3==4.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.5
+mypy-extensions==1.0.0
+networkx==3.2.1
+numpy==1.26.4
+oauthlib==3.2.2
+onnxruntime==1.17.1
+opentelemetry-api==1.23.0
+opentelemetry-exporter-otlp-proto-common==1.23.0
+opentelemetry-exporter-otlp-proto-grpc==1.23.0
+opentelemetry-instrumentation==0.44b0
+opentelemetry-instrumentation-asgi==0.44b0
+opentelemetry-instrumentation-fastapi==0.44b0
+opentelemetry-proto==1.23.0
+opentelemetry-sdk==1.23.0
+opentelemetry-semantic-conventions==0.44b0
+opentelemetry-util-http==0.44b0
+orjson==3.10.0
+overrides==7.7.0
+packaging==23.2
+pandas==2.2.1
+pillow==10.2.0
+posthog==3.5.0
+protobuf==4.25.3
+pulsar-client==3.4.0
+pyarrow==15.0.2
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydeck==0.8.1b0
+Pygments==2.17.2
+pypdf==4.1.0
+PyPika==0.48.9
+pyproject_hooks==1.0.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==2.0.0
+rich==13.7.1
+rpds-py==0.18.0
+rsa==4.9
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+sentence-transformers==2.6.1
+setuptools==69.2.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+SQLAlchemy==2.0.29
+starlette==0.36.3
+streamlit==1.32.2
+sympy==1.12
+tenacity==8.2.3
+threadpoolctl==3.4.0
+tokenizers==0.15.2
+toml==0.10.2
+toolz==0.12.1
+torch==2.2.2
+tornado==6.4
+tqdm==4.66.2
+transformers==4.39.2
+typer==0.11.0
+typing-inspect==0.9.0
+typing_extensions==4.10.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+uvloop==0.19.0
+watchfiles==0.21.0
+websocket-client==1.7.0
+websockets==12.0
+wrapt==1.16.0
+yarl==1.9.4
+zipp==3.18.1
diff --git a/st_app.py b/st_app.py
@@ -1,5 +1,5 @@
 import streamlit as st
-from app import *
+from rag import *
 
 st.set_page_config(page_title="LLM Search Titaninc", page_icon=':robot:')
 # st.header("Query PDF")
