A repo for example scripts that talk to documentation of any kind of the pattern: Ingest the source (typically public web documentation or PDFs) using Langchain, output a local vector-store with Langchain, then expose a chat window for "QA" using Streamlit UI. "RAG" (Retrieval Augmented Generation) queries against your configured LLM provider, see datascience's architecture diagram in the assets folder.
-
Notifications
You must be signed in to change notification settings - Fork 1
Example scripts to "QA" documentation, of the pattern: Ingest the source (public web documentation or PDFs) and output a local vector-store with Langchain, then expose a chat window for "QA" using Streamlit UI. simplest "RAG" (Retrieval Augmented Generation) queries using a configurable LLM provider
michael-s-downs/Langchain-DocTalks
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Example scripts to "QA" documentation, of the pattern: Ingest the source (public web documentation or PDFs) and output a local vector-store with Langchain, then expose a chat window for "QA" using Streamlit UI. simplest "RAG" (Retrieval Augmented Generation) queries using a configurable LLM provider
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published