> For the complete documentation index, see [llms.txt](https://changelog.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://changelog.graphlit.dev/april-2024/april-23-support-for-python-and-typescript-sdks-latest-openai-cohere-and-groq-models-bug-fixes.md).

# April 23: Support for Python and TypeScript SDKs, latest OpenAI, Cohere & Groq models, bug fixes

### New Features

* :bulb: Graphlit now supports a native Python SDK, using Pydantic types. The Python SDK is code-generated from the current GraphQL schema, but does not require GraphQL knowledge. You can find the latest PyPi package [here](https://pypi.org/project/graphlit-client/).  The Streamlit [sample applications](https://github.com/graphlit/graphlit-samples/tree/main/python) have been updated to use the new Python SDK.
* :bulb: Graphlit now supports a native Node.js SDK, using TypeScript types. The Node.js SDK is code-generated from the current GraphQL schema, but does not require GraphQL knowledge. You can find the latest NPM package [here](https://www.npmjs.com/package/graphlit-client).
* :bulb: Graphlit now supports the 2024-04-09 models in the OpenAI model service. `GPT4_TURBO-128K` will give the latest OpenAI GPT-4 model, following this model [list](https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4).  We have added the `GPT4_TURBO_128K_2024_04_09` enum to specify the new model.
* :bulb: Graphlit now supports [LLaMA3 70b, LLaMA3 8b and Gemma 7b models](https://console.groq.com/docs/models) in the Groq model service.
* :bulb: Graphlit now supports the [Command R and Command-R+](https://cohere.com/command) models in the Cohere model service.
* Added support for [Jina reranking](https://jina.ai/reranker/), using the `JINA` reranking model service type in the reranking retrieval strategy.
* Updated the Cohere reranking model to use the latest [v3.0](https://docs.cohere.com/reference/rerank) model.
* Increased the reliability of parsing LLM responses, in cases where they don't follow the JSON schema.
* :zap: Cleaned up nullability of GraphQL parameters, so parameters better reflect if they are required or optional, or allow nulls.
* :zap: Added missing `deleteWorkflows` and `deleteAllCollections` mutations.
* :zap: Split out reranking model service type as `RetrievalModelServiceTypes` enum. 

### Bugs Fixed

* GPLA-2114: Adding content to collections not syncing search index
* GPLA-2511: Failing to render any conversation sources with section retrieval and text content