haystack-core-integrations
haystack-core-integrations copied to clipboard
Additional packages (components, document stores and the likes) to extend the capabilities of Haystack version 2.0 and onwards
**Describe the bug** I encountered the following error when connecting `GoogleAIGeminiGenerator` with the `AnswerBuilder` component. ```python haystack.core.errors.PipelineConnectError: Cannot connect 'llm.replies' with 'answer_builder.replies': their declared input and output types do not...
### Related Issues - fixes #issue-number ### Proposed Changes: ### How did you test it? ### Notes for the reviewer ### Checklist - I have read the [contributors guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md) and...
**Describe the bug** When trying to use function calling with AWS Bedrock, the current integration ignore the tools keyword argument. ```python generator_json = AmazonBedrockChatGenerator( model="anthropic.claude-3-haiku-20240307-v1:0", aws_region_name=Secret.from_token("eu-west-3"), generation_kwargs={"temperature": 0, "max_tokens": 4096},...
## Summary and motivation Motivation from this issue [#6749](https://github.com/deepset-ai/haystack/issues/6749) raised by community members ## Detailed design Create a new document store for Azure AI search allowing operations of vector search,...
**Issue with Connection String Parsing in `PgvectorDocumentStore`** **Description:** Hi, I encountered a problem connecting to an Azure Cosmos DB using `PgvectorDocumentStore` from the `haystack_integrations.document_stores.pgvector` module. The issue seems to stem...
### Related Issues - fixes #936 ### Proposed Changes: Allow passing stream parameter to run() method to GoogleAIGeminiGenerator and GoogleVertexGeminiGenerator. This allows passing stream during the pipeline run and prevents...
**Describe the bug** `PineconeDocumentStore` raises an error when I try to index a document that was split by `DocumentSplitter`. Error message 👇 ```bash PineconeApiException: (400) Reason: Bad Request HTTP response...
### Related Issues - fixes #950 ### Proposed Changes: Implement a document store for [Azure AI Search.](https://learn.microsoft.com/en-us/azure/search/search-how-to-create-search-index?tabs=portal) ### How did you test it? Add unit tests for document store ###...
**Describe the bug** Running a simple embedding/indexing pipeline based on the pgvector integration ([example](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/pgvector/examples/example.py)). Having no problem when running `markdown` files, when running the pipeline through `pdf` files, I get...
At the moment, we only support OpenAI generator, but there has been demand in the community to use other models, such as Anthropic's Claude LLMs. Below is an example from...