-
LangChain is a toolkit around all things LLMs, including RAG. We use it to parse our documents or codebase and generate a vector database from it. In our simple RAG system, we specify which file endings (.rb) and which programming language (Ruby) our documents have.
-
Scout Monitoring
Free Django app performance insights with Scout Monitoring. Get Scout setup in minutes, and let us sweat the small stuff. A couple lines in settings.py is all you need to start monitoring your apps. Sign up for our free tier today.
-
The ingestion of programming source code into an LLM with LangChain was initially only supported for Python, C and a few others languages. Then this issue proposed the usage of a parser library like Tree-sitter to facilitate adding support for many more languages. The discussion is worth reading.
-
For testing purposes we will use our RAG system on a popular open source Elixir package, the Phoenix Framework.