This repo is an implementation of a chatbot specifically focused on question answering over the LangChain documentation.

Website: chat.langchain.dev

Hugging Face Spage: huggingface.co/spaces/hwchase17/chat-langchain

Blog Post: blog.langchain.dev/langchain-chat/

There are two components: ingestion and question-answering.

Ingestion has the following steps:

1. Pull html from documentation site
2. Parse html with BeautifulSoup
3. Split documents with LangChain's TextSplitter
4. Create a vectorstore of embeddings, using LangChain's vectorstore wrapper (with OpenAI's embeddings and Weaviate's vectorstore)

Question-Answering has the following steps:

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
3. Pass the standalone question and relevant documents to GPT-3 to generate a final answer

Coming soon.

1. Pull html from documentation site
2. Parse html with BeautifulSoup
3. Split documents with LangChain's TextSplitter
4. Create a vectorstore of embeddings, using LangChain's [vectorstore wrapper](https://langchain.readthedocs.io/en/latest/modules/utils/combine_docs_examples/v