log webadmin url on startup (#194)

unpaginate summart retrieval (#191)

contributing.md (#182)

fix/AuzreOpenAI embeddings and LLM deployment name (#172)

solves "The API deployment for this resource does not exist" for LLM and
embedding models deployed in Azure OpenAI by deployment name supported
in tmc/langchaingo#253

We can't Validate OpenAI LLM model names from hard-coded list in Azure
because the model name parameter in API request is a deployment name,
and while Microsoft advises us to use the model name as deployment name,
we did not listen, and I didn't want to coordinate redeploying with a
different name on a Friday.

This also permits use of customized models that can be deployed in Azure
side-by-side base models as added benefit so I think it was worthwhile.

Co-authored-by: Claudia Justice Kane <claudia.hardman@mattel.com>

LlamaIndex references (#166)

fix parseDocumentJSONQuery

sdk on README

Beta/1.9.0 beta1: Fix ranking issue arising from normalizing scores (…

…#150)

* fix ranking issue resulting from late change to normalized score

* beta config

* beta tag and loosen docker compose version

Document VectorStore 🔥⭐️; Refactoring (#143)

- DocumentStore, a vector store for texts
- Embedding pipeline
- Refactoring Store infrastructure

BugFix: failure to acquire lock; nil pointer dereference (#132)

* only persist session metadata when metadata is present

* check for error before dereferencing

* don't update message metadata when extractor returns no metadata

* only put message metadata if len(metadata) > 0

* putmessage: update metdata outside of message insert tx