wejick / gochain Goto Github PK

On LangChain there is the kwargs where it's passed from front to back, with the nature of Python's dynamic typing this kwargs can be reused by many layers from agent, to chain until model.
However, to have an idiomatic Go developer experience, that model is not ideal. If we talk about the perfect way, it should use a functional option pattern.

Need more research on how this model will looks like.

In LangChain there's tracing functionality where we can see all the LLM invocation and use it to debug the implementation.

This functionality will be useful to have, however the API of langchain-server is opaque. I don't know where to get the source of it or any possibility to reuse it.
I would love to reuse any available tracer and UI, one idea is probably to use OpenTelemetry. I don't think it has proper UI for development need.

For implementation detail, we can use callback.

As right now elasticsearch is still one of the most popular search engine, which happen also has decent support of vector search. Having it as datastore is very make sense step. In other side having Metada on it will be easier than on Weaviate which you need to know beforehand what are field to return.

Today vector store search function will still do vector based search to the database. Instead of having vector parameter, it has string based parameter which will be converted to vector later.

Is it better for search to do a nonvector search instead if applicable?
do we need an extra option for this? what will be the default behavior?

How about hybrid search?

#9

The current github action only test the unit test. need to investigate how to run the integration test on github action as well.

Need to investigate if elastic support dynamic dimension, if yes we may not need to do this

#9