ugh

app.py

@@ -11,6 +11,9 @@ 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
+from tqdm.asyncio import tqdm_asyncio
+import asyncio
+from tqdm.asyncio import tqdm
 
 # GLOBAL SCOPE - ENTIRE APPLICATION HAS ACCESS TO VALUES SET IN THIS SCOPE #
 # ---- ENV VARIABLES ---- # 
@@ -43,32 +46,63 @@ documents = document_loader.load()
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
 split_documents = text_splitter.split_documents(documents)
 
-"""print("initializing embeddings")
 hf_embeddings = HuggingFaceEndpointEmbeddings(
     model=HF_EMBED_ENDPOINT,
     task="feature-extraction",
     huggingfacehub_api_token=HF_TOKEN,
 )
 
-if os.path.exists("./data/vectorstore"):
-    vectorstore = FAISS.load_local(
-        "./data/vectorstore", 
-        hf_embeddings, 
-        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()
-    print("Loaded Vectorstore")
-else:
+async def add_documents_async(vectorstore, documents):
+    await vectorstore.aadd_documents(documents)
+
+async def process_batch(vectorstore, batch, is_first_batch, pbar):
+    if is_first_batch:
+        result = await FAISS.afrom_documents(batch, hf_embeddings)
+    else:
+        await add_documents_async(vectorstore, batch)
+        result = vectorstore
+    pbar.update(len(batch))
+    return result
+
+async def main():
     print("Indexing Files")
-    #os.makedirs("./data/vectorstore", exist_ok=True)
-    for i in range(0, len(split_documents), 32):
-        if i == 0:
-            vectorstore = FAISS.from_documents(split_documents[i:i+32], hf_embeddings)
-            continue
-        vectorstore.add_documents(split_documents[i:i+32])
-    #vectorstore.save_local("./data/vectorstore")
+    
+    vectorstore = None
+    batch_size = 32
+    
+    batches = [split_documents[i:i+batch_size] for i in range(0, len(split_documents), batch_size)]
+    
+    async def process_all_batches():
+        nonlocal vectorstore
+        tasks = []
+        pbars = []
+        
+        for i, batch in enumerate(batches):
+            pbar = tqdm(total=len(batch), desc=f"Batch {i+1}/{len(batches)}", position=i)
+            pbars.append(pbar)
+            
+            if i == 0:
+                vectorstore = await process_batch(None, batch, True, pbar)
+            else:
+                tasks.append(process_batch(vectorstore, batch, False, pbar))
+        
+        if tasks:
+            await asyncio.gather(*tasks)
+        
+        for pbar in pbars:
+            pbar.close()
+    
+    await process_all_batches()
+    
+    hf_retriever = vectorstore.as_retriever()
+    print("\nIndexing complete. Vectorstore is ready for use.")
+    return hf_retriever
+
+async def run():
+    retriever = await main()
+    return retriever
 
-hf_retriever = vectorstore.as_retriever()"""
+hf_retriever = asyncio.run(run())
 
 # -- AUGMENTED -- #
 """
@@ -83,10 +117,7 @@ You are a helpful assistant. You answer user questions based on provided context
 User Query:
 {query}
 
-<|start_header_id|>assistant<|end_header_id|>
-"""
-
-"""Context:
+Context:
 {context}<|eot_id|>
 
 <|start_header_id|>assistant<|end_header_id|>
@@ -129,20 +160,13 @@ async def start_chat():
 
     The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
     """
-    print("entering on_chat_start")
-    """lcel_rag_chain = (
+
+    lcel_rag_chain = (
         {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
         | rag_prompt | hf_llm
-    )"""
-    lcel_rag_chain = {"query": itemgetter("query")} | rag_prompt | hf_llm
+    )
 
-    try:
-        # Attempt to set up session normally
-        cl.user_session.set("lcel_rag_chain", lcel_rag_chain)
-    except KeyError:
-        print("Reinitializing session due to disconnection.")
-        cl.user_session.clear()
-        cl.user_session.set("lcel_rag_chain", lcel_rag_chain)
+    cl.user_session.set("lcel_rag_chain", lcel_rag_chain)
 
 @cl.on_message  
 async def main(message: cl.Message):
@@ -153,10 +177,6 @@ async def main(message: cl.Message):
 
     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.
     """
-    print("entering on_message")
-    msg = cl.Message(content="Processing your request... this may take a moment.")
-    await msg.send()
-
     lcel_rag_chain = cl.user_session.get("lcel_rag_chain")
 
     msg = cl.Message(content="")

chainlit.md

@@ -1 +1 @@
-# FILL OUT YOUR CHAINLIT MD HERE WITH A DESCRIPTION OF YOUR APPLICATION
+This bot to help users explore the writings of Paul Graham. 

requirements.txt

@@ -1,354 +1,132 @@
-#
-# This file is autogenerated by pip-compile with Python 3.9
-# by the following command:
-#
-#    pip-compile requirement.in
-#
 aiofiles==23.2.1
-    # via chainlit
 aiohappyeyeballs==2.4.3
-    # via aiohttp
-aiohttp==3.10.9
-    # via
-    #   langchain
-    #   langchain-community
+aiohttp==3.10.8
 aiosignal==1.3.1
-    # via aiohttp
 annotated-types==0.7.0
-    # via pydantic
 anyio==3.7.1
-    # via
-    #   asyncer
-    #   httpx
-    #   starlette
-    #   watchfiles
 async-timeout==4.0.3
-    # via
-    #   aiohttp
-    #   langchain
 asyncer==0.0.2
-    # via chainlit
 attrs==24.2.0
-    # via aiohttp
 bidict==0.23.1
-    # via python-socketio
 certifi==2024.8.30
-    # via
-    #   httpcore
-    #   httpx
-    #   requests
-chainlit==1.1.302
-    # via -r requirement.in
+chainlit==0.7.700
 charset-normalizer==3.3.2
-    # via requests
-chevron==0.14.0
-    # via literalai
 click==8.1.7
-    # via
-    #   chainlit
-    #   uvicorn
 dataclasses-json==0.5.14
-    # via
-    #   chainlit
-    #   langchain-community
-deprecated==1.2.14
-    # via
-    #   opentelemetry-api
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
-    #   opentelemetry-semantic-conventions
+Deprecated==1.2.14
+distro==1.9.0
 exceptiongroup==1.2.2
-    # via anyio
 faiss-cpu==1.8.0.post1
-    # via -r requirement.in
-fastapi==0.110.3
-    # via chainlit
+fastapi==0.100.1
+fastapi-socketio==0.0.10
 filelock==3.16.1
-    # via
-    #   huggingface-hub
-    #   torch
-    #   transformers
 filetype==1.2.0
-    # via chainlit
 frozenlist==1.4.1
-    # via
-    #   aiohttp
-    #   aiosignal
 fsspec==2024.9.0
-    # via
-    #   huggingface-hub
-    #   torch
 googleapis-common-protos==1.65.0
-    # via
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
 greenlet==3.1.1
-    # via sqlalchemy
 grpcio==1.66.2
-    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio-tools==1.62.3
 h11==0.14.0
-    # via
-    #   httpcore
-    #   uvicorn
-    #   wsproto
-httpcore==1.0.6
-    # via httpx
-httpx==0.27.2
-    # via
-    #   chainlit
-    #   langsmith
-    #   literalai
+h2==4.1.0
+hpack==4.0.0
+httpcore==0.17.3
+httpx==0.24.1
 huggingface-hub==0.25.1
-    # via
-    #   langchain-huggingface
-    #   sentence-transformers
-    #   tokenizers
-    #   transformers
+hyperframe==6.0.1
 idna==3.10
-    # via
-    #   anyio
-    #   httpx
-    #   requests
-    #   yarl
-importlib-metadata==8.4.0
-    # via opentelemetry-api
-jinja2==3.1.4
-    # via torch
+importlib_metadata==8.4.0
+Jinja2==3.1.4
+jiter==0.5.0
 joblib==1.4.2
-    # via scikit-learn
 jsonpatch==1.33
-    # via langchain-core
 jsonpointer==3.0.0
-    # via jsonpatch
-langchain==0.2.5
-    # via
-    #   -r requirement.in
-    #   langchain-community
-langchain-community==0.2.5
-    # via -r requirement.in
-langchain-core==0.2.9
-    # via
-    #   -r requirement.in
-    #   langchain
-    #   langchain-community
-    #   langchain-huggingface
-    #   langchain-text-splitters
-langchain-huggingface==0.0.3
-    # via -r requirement.in
-langchain-text-splitters==0.2.1
-    # via
-    #   -r requirement.in
-    #   langchain
-langsmith==0.1.132
-    # via
-    #   langchain
-    #   langchain-community
-    #   langchain-core
-lazify==0.4.0
-    # via chainlit
-literalai==0.0.604
-    # via chainlit
-markupsafe==3.0.0
-    # via jinja2
+langchain==0.3.0
+langchain-community==0.3.0
+langchain-core==0.3.1
+langchain-huggingface==0.1.0
+langchain-openai==0.2.0
+langchain-qdrant==0.1.4
+langchain-text-splitters==0.3.0
+langsmith==0.1.121
+Lazify==0.4.0
+MarkupSafe==2.1.5
 marshmallow==3.22.0
-    # via dataclasses-json
 mpmath==1.3.0
-    # via sympy
 multidict==6.1.0
-    # via
-    #   aiohttp
-    #   yarl
 mypy-extensions==1.0.0
-    # via typing-inspect
 nest-asyncio==1.6.0
-    # via chainlit
 networkx==3.2.1
-    # via torch
 numpy==1.26.4
-    # via
-    #   chainlit
-    #   faiss-cpu
-    #   langchain
-    #   langchain-community
-    #   scikit-learn
-    #   scipy
-    #   transformers
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvtx-cu12==12.1.105
+openai==1.51.0
 opentelemetry-api==1.27.0
-    # via
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
-    #   opentelemetry-instrumentation
-    #   opentelemetry-sdk
-    #   opentelemetry-semantic-conventions
-    #   uptrace
 opentelemetry-exporter-otlp==1.27.0
-    # via uptrace
 opentelemetry-exporter-otlp-proto-common==1.27.0
-    # via
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
 opentelemetry-exporter-otlp-proto-grpc==1.27.0
-    # via opentelemetry-exporter-otlp
 opentelemetry-exporter-otlp-proto-http==1.27.0
-    # via opentelemetry-exporter-otlp
 opentelemetry-instrumentation==0.48b0
-    # via uptrace
 opentelemetry-proto==1.27.0
-    # via
-    #   opentelemetry-exporter-otlp-proto-common
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
 opentelemetry-sdk==1.27.0
-    # via
-    #   opentelemetry-exporter-otlp-proto-grpc
-    #   opentelemetry-exporter-otlp-proto-http
-    #   uptrace
 opentelemetry-semantic-conventions==0.48b0
-    # via opentelemetry-sdk
 orjson==3.10.7
-    # via langsmith
 packaging==23.2
-    # via
-    #   chainlit
-    #   faiss-cpu
-    #   huggingface-hub
-    #   langchain-core
-    #   literalai
-    #   marshmallow
-    #   transformers
 pillow==10.4.0
-    # via sentence-transformers
+portalocker==2.10.1
 protobuf==4.25.5
-    # via
-    #   googleapis-common-protos
-    #   opentelemetry-proto
 pydantic==2.9.2
-    # via
-    #   chainlit
-    #   fastapi
-    #   langchain
-    #   langchain-core
-    #   langsmith
-    #   literalai
-pydantic-core==2.23.4
-    # via pydantic
-pyjwt==2.9.0
-    # via chainlit
+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
-    # via
-    #   -r requirement.in
-    #   chainlit
 python-engineio==4.9.1
-    # via python-socketio
-python-multipart==0.0.9
-    # via chainlit
+python-graphql-client==0.4.3
+python-multipart==0.0.6
 python-socketio==5.11.4
-    # via chainlit
-pyyaml==6.0.2
-    # via
-    #   huggingface-hub
-    #   langchain
-    #   langchain-community
-    #   langchain-core
-    #   transformers
+PyYAML==6.0.2
+qdrant-client==1.11.2
 regex==2024.9.11
-    # via transformers
 requests==2.32.3
-    # via
-    #   huggingface-hub
-    #   langchain
-    #   langchain-community
-    #   langsmith
-    #   opentelemetry-exporter-otlp-proto-http
-    #   requests-toolbelt
-    #   transformers
-requests-toolbelt==1.0.0
-    # via langsmith
 safetensors==0.4.5
-    # via transformers
 scikit-learn==1.5.2
-    # via sentence-transformers
 scipy==1.13.1
-    # via
-    #   scikit-learn
-    #   sentence-transformers
 sentence-transformers==3.1.1
-    # via langchain-huggingface
 simple-websocket==1.0.0
-    # via python-engineio
 sniffio==1.3.1
-    # via
-    #   anyio
-    #   httpx
-sqlalchemy==2.0.35
-    # via
-    #   langchain
-    #   langchain-community
-starlette==0.37.2
-    # via
-    #   chainlit
-    #   fastapi
+SQLAlchemy==2.0.35
+starlette==0.27.0
 sympy==1.13.3
-    # via torch
 syncer==2.0.3
-    # via chainlit
 tenacity==8.5.0
-    # via
-    #   langchain
-    #   langchain-community
-    #   langchain-core
 threadpoolctl==3.5.0
-    # via scikit-learn
+tiktoken==0.7.0
 tokenizers==0.20.0
-    # via
-    #   langchain-huggingface
-    #   transformers
-tomli==2.0.2
-    # via chainlit
-torch==2.2.2
-    # via sentence-transformers
+tomli==2.0.1
+torch==2.4.1
 tqdm==4.66.5
-    # via
-    #   huggingface-hub
-    #   sentence-transformers
-    #   transformers
-transformers==4.45.2
-    # via
-    #   langchain-huggingface
-    #   sentence-transformers
-typing-extensions==4.12.2
-    # via
-    #   fastapi
-    #   huggingface-hub
-    #   multidict
-    #   opentelemetry-sdk
-    #   pydantic
-    #   pydantic-core
-    #   sqlalchemy
-    #   starlette
-    #   torch
-    #   typing-inspect
-    #   uvicorn
+transformers==4.45.1
+triton==3.0.0
 typing-inspect==0.9.0
-    # via dataclasses-json
-uptrace==1.27.0
-    # via chainlit
+typing_extensions==4.12.2
+uptrace==1.26.0
 urllib3==2.2.3
-    # via requests
-uvicorn==0.25.0
-    # via chainlit
+uvicorn==0.23.2
 watchfiles==0.20.0
-    # via chainlit
+websockets==13.1
 wrapt==1.16.0
-    # via
-    #   deprecated
-    #   opentelemetry-instrumentation
 wsproto==1.2.0
-    # via simple-websocket
 yarl==1.13.1
-    # via aiohttp
-zipp==3.20.2
-    # via importlib-metadata
-
-# The following packages are considered to be unsafe in a requirements file:
-# setuptools
+zipp==3.20.2