Freezaa9 comments

Results 15 comments of


                                            Freezaa9

More pk chunking handling

up. Would be nice to be able to use the "parent" field as here: https://developer.salesforce.com/docs/atlas.en-us.api_asynch.meta/api_asynch/async_api_headers_enable_pk_chunking.htm For example I need it to get the AccountHistory object with Account as parent.

Add new resources for Vertex AI Vector Search (formally known as, Vertex AI Matching Engine)

Thanks @davidcavazos Any news about including this natively?

Getting "RuntimeError: Tool context error detected. This can occur due to parallelization." while invoking a chain using langchain_google_vertexai

Look like it is fixed: https://github.com/googleapis/python-aiplatform/issues/3838 in google-cloud-aiplatform == 1.54.0

Support for the sparse embeddings

Hello, would be interested also. But I think each vector DB should be separated. So for a hybrid search it would be - One Dense embedding vector DB (using the...

AxiosError: maxContentLength size of -1 exceeded

same error here while calling streaming api

Added latest PGVector features

Thanks @danielfornarini for this PR we need it.

Added latest PGVector features

I've been testing this pr for a project, and I don't see issues. It feels like this repo is a bit dead ?

Added latest PGVector features

I'm losing hope, meanwhile cloud sql postgres langchain implementation did implement some of the latest feature of pgvector: https://github.com/googleapis/langchain-google-cloud-sql-pg-python

Compatibility with langchain-core >= 1.0.0

Same issue, numerous library now depends on langchain-core >= 1.0.0

thread_id too long for Postgres checkpoint

It could fix the issue, but then you won't have the same thread id in PostgreSQL and complicate the ease of checkpointing usage and debugging