use solution app

app.py

@@ -1,5 +1,6 @@
 import os
 import chainlit as cl
+from dotenv import load_dotenv
 from operator import itemgetter
 from langchain_huggingface import HuggingFaceEndpoint
 from langchain_community.document_loaders import TextLoader
@@ -7,53 +8,75 @@ from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
 from langchain_huggingface import HuggingFaceEndpointEmbeddings
 from langchain_core.prompts import PromptTemplate
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
 from langchain.schema.runnable.config import RunnableConfig
 
+# GLOBAL SCOPE - ENTIRE APPLICATION HAS ACCESS TO VALUES SET IN THIS SCOPE #
+# ---- ENV VARIABLES ---- # 
+"""
+This function will load our environment file (.env) if it is present.
+
+NOTE: Make sure that .env is in your .gitignore file - it is by default, but please ensure it remains there.
+"""
+load_dotenv()
+
+"""
+We will load our environment variables here.
+"""
 HF_LLM_ENDPOINT = os.environ["HF_LLM_ENDPOINT"]
 HF_EMBED_ENDPOINT = os.environ["HF_EMBED_ENDPOINT"]
 HF_TOKEN = os.environ["HF_TOKEN"]
 
-# -- Data loading, embeddings, vector store --
+# ---- GLOBAL DECLARATIONS ---- #
+
+# -- RETRIEVAL -- #
+"""
+1. Load Documents from Text File
+2. Split Documents into Chunks
+3. Load HuggingFace Embeddings (remember to use the URL we set above)
+4. Index Files if they do not exist, otherwise load the vectorstore
+"""
 document_loader = TextLoader("./data/paul_graham_essays.txt")
 documents = document_loader.load()
 
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
 split_documents = text_splitter.split_documents(documents)
-print("chunked docs")
 
 hf_embeddings = HuggingFaceEndpointEmbeddings(
     model=HF_EMBED_ENDPOINT,
     task="feature-extraction",
     huggingfacehub_api_token=HF_TOKEN,
 )
-print("initialized embeddings")
-
-vectorstore_file = "./data/vectorstore"
-vectorstore = None
 
-if os.path.exists(vectorstore_file):
-   vectorstore = FAISS.load_local(
-        vectorstore_file, 
+if os.path.exists("./data/vectorstore"):
+    vectorstore = FAISS.load_local(
+        "./data/vectorstore", 
         hf_embeddings, 
-        allow_dangerous_deserialization=True 
+        allow_dangerous_deserialization=True # this is necessary to load the vectorstore from disk as it's stored as a `.pkl` file.
     )
-   hf_retriever = vectorstore.as_retriever()
+    hf_retriever = vectorstore.as_retriever()
+    print("Loaded Vectorstore")
 else:
+    print("Indexing Files")
+    os.makedirs("./data/vectorstore", exist_ok=True)
     for i in range(0, len(split_documents), 32):
-        print(f"Embedding batch {i}")
         if i == 0:
             vectorstore = FAISS.from_documents(split_documents[i:i+32], hf_embeddings)
-            print("initialized vectorstore")
             continue
         vectorstore.add_documents(split_documents[i:i+32])
-        hf_retriever = vectorstore.as_retriever()
-print("Created vectorstore")
+    vectorstore.save_local("./data/vectorstore")
 
-## -- System prompt --
+hf_retriever = vectorstore.as_retriever()
+
+# -- AUGMENTED -- #
+"""
+1. Define a String Template
+2. Create a Prompt Template from the String Template
+"""
 RAG_PROMPT_TEMPLATE = """\
 <|start_header_id|>system<|end_header_id|>
-You are a helpful expert in tech and entrepreneurship. You answer user questions based on provided context. 
-If you can't answer the question with the provided context, say you don't know.<|eot_id|>
+You are a helpful assistant. You answer user questions based on provided context. If you can't answer the question with the provided context, say you don't know.<|eot_id|>
 
 <|start_header_id|>user<|end_header_id|>
 User Query:
@@ -64,10 +87,13 @@ Context:
 
 <|start_header_id|>assistant<|end_header_id|>
 """
+
 rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
-print("created prompt")
 
-## -- LLM endpoint --
+# -- GENERATION -- #
+"""
+1. Create a HuggingFaceEndpoint for the LLM
+"""
 hf_llm = HuggingFaceEndpoint(
     endpoint_url=HF_LLM_ENDPOINT,
     max_new_tokens=512,
@@ -77,10 +103,14 @@ hf_llm = HuggingFaceEndpoint(
     repetition_penalty=1.15,
     huggingfacehub_api_token=HF_TOKEN,
 )
-print("initialized endpoint")
 
 @cl.author_rename
 def rename(original_author: str):
+    """
+    This function can be used to rename the 'author' of a message. 
+
+    In this case, we're overriding the 'Assistant' author to be 'Paul Graham Essay Bot'.
+    """
     rename_dict = {
         "Assistant" : "Paul Graham Essay Bot"
     }
@@ -88,17 +118,34 @@ def rename(original_author: str):
 
 @cl.on_chat_start
 async def start_chat():
+    """
+    This function will be called at the start of every user session. 
+
+    We will build our LCEL RAG chain here, and store it in the user session. 
+
+    The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
+    """
+
     lcel_rag_chain = (
         {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
         | rag_prompt | hf_llm
     )
+
     cl.user_session.set("lcel_rag_chain", lcel_rag_chain)
-    await cl.Message(content="I'm ready to chat about tech and entrepreneurship!").send()
 
 @cl.on_message  
 async def main(message: cl.Message):
+    """
+    This function will be called every time a message is recieved from a session.
+
+    We will use the LCEL RAG chain to generate a response to the user query.
+
+    The LCEL RAG chain is stored in the user session, and is unique to each user session - this is why we can access it here.
+    """
     lcel_rag_chain = cl.user_session.get("lcel_rag_chain")
+
     msg = cl.Message(content="")
+
     for chunk in await cl.make_async(lcel_rag_chain.stream)(
         {"query": message.content},
         config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),

chainlit.md

@@ -1 +1 @@
-This RAG app uses HuggingFace-hosted enpoints for its embeddings (Snowflake Arctic) and its LLM (Llama 3.1 8B). It uses Paul Graham's essays to discuss entrepreneurship and tech.
+# FILL OUT YOUR CHAINLIT MD HERE WITH A DESCRIPTION OF YOUR APPLICATION

requirements.txt

@@ -1,8 +1,100 @@
-chainlit==1.1.302
-langchain==0.2.5
-langchain_community==0.2.5
-langchain_core==0.2.9
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.8
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==3.7.1
+async-timeout==4.0.3
+asyncer==0.0.2
+attrs==24.2.0
+bidict==0.23.1
+certifi==2024.8.30
+chainlit==0.7.700
+charset-normalizer==3.3.2
+click==8.1.7
+dataclasses-json==0.5.14
 langchain_huggingface==0.0.3
-langchain_text_splitters==0.2.1
+Deprecated==1.2.14
+distro==1.9.0
+exceptiongroup==1.2.2
+fastapi==0.100.1
+fastapi-socketio==0.0.10
+filetype==1.2.0
+frozenlist==1.4.1
+googleapis-common-protos==1.65.0
+greenlet==3.1.1
+grpcio==1.66.2
+grpcio-tools==1.62.3
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==0.17.3
+httpx==0.24.1
+hyperframe==6.0.1
+idna==3.10
+importlib_metadata==8.4.0
+jiter==0.5.0
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.0
+langchain-community==0.3.0
+langchain-core==0.3.1
+langchain-openai==0.2.0
+langchain-qdrant==0.1.4
+langchain-text-splitters==0.3.0
+langsmith==0.1.121
+Lazify==0.4.0
+marshmallow==3.22.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+numpy==1.26.4
+openai==1.51.0
+opentelemetry-api==1.27.0
+opentelemetry-exporter-otlp==1.27.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
+opentelemetry-exporter-otlp-proto-grpc==1.27.0
+opentelemetry-exporter-otlp-proto-http==1.27.0
+opentelemetry-instrumentation==0.48b0
+opentelemetry-proto==1.27.0
+opentelemetry-sdk==1.27.0
+opentelemetry-semantic-conventions==0.48b0
+orjson==3.10.7
+packaging==23.2
+portalocker==2.10.1
+protobuf==4.25.5
+pydantic==2.9.2
+pydantic-settings==2.5.2
+pydantic_core==2.23.4
+PyJWT==2.9.0
+PyMuPDF==1.24.10
+PyMuPDFb==1.24.10
 python-dotenv==1.0.1
-faiss-cpu
+python-engineio==4.9.1
+python-graphql-client==0.4.3
+python-multipart==0.0.6
+python-socketio==5.11.4
+PyYAML==6.0.2
+qdrant-client==1.11.2
+regex==2024.9.11
+requests==2.32.3
+simple-websocket==1.0.0
+sniffio==1.3.1
+SQLAlchemy==2.0.35
+starlette==0.27.0
+syncer==2.0.3
+tenacity==8.5.0
+tiktoken==0.7.0
+tomli==2.0.1
+tqdm==4.66.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+uptrace==1.26.0
+urllib3==2.2.3
+uvicorn==0.23.2
+watchfiles==0.20.0
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+yarl==1.13.1
+zipp==3.20.2