haystack-core-integrations
haystack-core-integrations copied to clipboard
deepset-ai
Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards
As reported in #2038, when working on fixing types, I discovered that currently the Weave Tracer violates of the Liskov Substitution Principle and fixing this does not seem straightforward. https://github.com/deepset-ai/haystack-core-integrations/blob/14fd1b8b276a62a5630e474e047ecaf1816e904b/integrations/weights_and_biases_weave/src/haystack_integrations/tracing/weave/tracer.py#L157-L159...
## Summary and motivation **ChatGenerator Motivation:** from https://github.com/deepset-ai/haystack-core-integrations/issues/1958 > When using OpenAIChatGenerator with OpenAI-compatible APIs that return additional custom parameters in the response delta (such as reasoning_content, thinking_content, or other...
# Feature Request: Support for Custom Response Parameters in OpenAIChatGenerator ## Problem Description When using `OpenAIChatGenerator` with OpenAI-compatible APIs that return additional custom parameters in the response delta (such as...
We should add a `run_async` implementation for `LlamaCppChatGenerator` since we have `AsyncPipeline` available.
**Is your feature request related to a problem? Please describe.** Currently, tracing in Haystack is globally enabled or disabled for all pipelines via the tracer configuration (e.g., Langfuse). This means...
**Is your feature request related to a problem? Please describe.** I cannot use a (small) local LLM or customized prompts for evaluation of the RAG pipeline output. Smaller LLMs (e.g.,...
**Is your feature request related to a problem? Please describe.** Unlike the `VertexAIGeminiChatGenerator`, the `VertexAIGeminiGenerator` class does not return any usage metadata (prompt tokens, etc) in the response. It throws...
**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...
Currently Alloydb has [integration with Langchain](https://github.com/googleapis/langchain-google-alloydb-pg-python/) but no integration is done with Haystack. Basically, as other integrations with vector database, it would be really helpful to have it with Alloydb...
Metadata
Owner
Metadata
Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards