Fix all broken issues up to now

.gitignore

@@ -136,4 +136,6 @@ dmypy.json
 .DS_Store
 
 vectorstore.pkl
-langchain.readthedocs.io/
+python.langchain.com/
+
+.venv

README.md

@@ -30,11 +30,11 @@ There are two components: ingestion and question-answering.
 Ingestion has the following steps:
 
 1. Pull html from documentation site
-2. Load html with LangChain's [ReadTheDocs Loader](https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/readthedocs_documentation.html)
-3. Split documents with LangChain's [TextSplitter](https://langchain.readthedocs.io/en/latest/reference/modules/text_splitter.html)
+2. Load html with LangChain's [ReadTheDocs Loader](https://python.langchain.com/en/latest/modules/document_loaders/examples/readthedocs_documentation.html)
+3. Split documents with LangChain's [TextSplitter](https://python.langchain.com/en/latest/reference/modules/text_splitter.html)
 4. Create a vectorstore of embeddings, using LangChain's [vectorstore wrapper](https://python.langchain.com/en/latest/modules/indexes/vectorstores.html) (with OpenAI's embeddings and FAISS vectorstore).
 
-Question-Answering has the following steps, all handled by [ChatVectorDBChain](https://langchain.readthedocs.io/en/latest/modules/indexes/chain_examples/chat_vector_db.html):
+Question-Answering has the following steps, all handled by [ChatVectorDBChain](https://python.langchain.com/en/latest/modules/indexes/chain_examples/chat_vector_db.html):
 
 1. Given the chat history and new user input, determine what a standalone question would be (using GPT-3).
 2. Given that standalone question, look up relevant documents from the vectorstore.

ingest.py

@@ -9,7 +9,7 @@
 
 def ingest_docs():
     """Get documents from web pages."""
-    loader = ReadTheDocsLoader("langchain.readthedocs.io/en/latest/")
+    loader = ReadTheDocsLoader("python.langchain.com/en/latest/")
     raw_documents = loader.load()
     text_splitter = RecursiveCharacterTextSplitter(
         chunk_size=1000,

ingest.sh

@@ -2,5 +2,5 @@
 # This involves scraping the data from the web and then cleaning up and putting in Weaviate.
 # Error if any command fails
 set -e
-wget -r -A.html https://langchain.readthedocs.io/en/latest/
+wget -r -A.html https://python.langchain.com/en/latest/
 python3 ingest.py

main.py

@@ -41,7 +41,7 @@ async def websocket_endpoint(websocket: WebSocket):
     qa_chain = get_chain(vectorstore, question_handler, stream_handler)
     # Use the below line instead of the above line to enable tracing
     # Ensure `langchain-server` is running
-    # qa_chain = get_chain(vectorstore, question_handler, stream_handler, tracing=True)
+    # qa_chain = await get_chain(vectorstore, question_handler, stream_handler, tracing=True)
 
     while True:
         try:

query_data.py

@@ -1,7 +1,7 @@
 """Create a ChatVectorDBChain for question/answering."""
-from langchain.callbacks.base import AsyncCallbackManager
+from langchain.callbacks.manager import AsyncCallbackManager
 from langchain.callbacks.tracers import LangChainTracer
-from langchain.chains import ChatVectorDBChain
+from langchain.chains import ConversationalRetrievalChain
 from langchain.chains.chat_vector_db.prompts import (CONDENSE_QUESTION_PROMPT,
                                                      QA_PROMPT)
 from langchain.chains.llm import LLMChain
@@ -12,9 +12,9 @@
 
 def get_chain(
     vectorstore: VectorStore, question_handler, stream_handler, tracing: bool = False
-) -> ChatVectorDBChain:
-    """Create a ChatVectorDBChain for question/answering."""
-    # Construct a ChatVectorDBChain with a streaming llm for combine docs
+) -> ConversationalRetrievalChain:
+    """Create a ConversationalRetrievalChain for question/answering."""
+    # Construct a ConversationalRetrievalChain with a streaming llm for combine docs
     # and a separate, non-streaming llm for question generation
     manager = AsyncCallbackManager([])
     question_manager = AsyncCallbackManager([question_handler])
@@ -45,8 +45,8 @@ def get_chain(
         streaming_llm, chain_type="stuff", prompt=QA_PROMPT, callback_manager=manager
     )
 
-    qa = ChatVectorDBChain(
-        vectorstore=vectorstore,
+    qa = ConversationalRetrievalChain(
+        retriever=vectorstore.as_retriever(),
         combine_docs_chain=doc_chain,
         question_generator=question_generator,
         callback_manager=manager,

requirements.txt

@@ -11,3 +11,4 @@ faiss-cpu
 bs4
 unstructured
 libmagic
+tiktoken