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
**Is your feature request related to a problem? Please describe.** GoogleAIGeminiChatGenerator only accepts a flat `List[Tool]` for tools. Since Haystack 2.13 added the higher-level `Toolset` abstraction (see deepset-ai/haystack#9177), projects that...
**Is your feature request related to a problem? Please describe.** `OllamaChatGenerator` only accepts a flat `List[Tool]` for tools. Since Haystack 2.13 added the higher-level `Toolset` abstraction (see deepset-ai/haystack#9177), projects that...
### Related Issues (None) ### Proposed Changes: Currently, the `metadata_fields` init parameter only allowed a few custom simple value types to be mapped (e.g., no nested metadata) and also hardcoded...
In #1623, we are making our Chat Generators compatible with the new `deserialize_tools_or_toolset_inplace`. After Haystack 2.13.0 release, we should: - remove the import fallback workaround introduced in #1623 - add...
**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 [...] I am building a...
**Is your feature request related to a problem? Please describe.** AWS Bedrock Guardrails can be [triggered](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-use-converse-api.html#guardrails-use-converse-api-call-configure) with the Converse API directly using the [guardrailConfig](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html#API_runtime_Converse_RequestSyntax) parameter. Currently, the AmazonBedrockChatGenerator [api](https://github.com/deepset-ai/haystack-core-integrations/blob/cf5aaa70a92c601d656ae30d493b7e87c2eb601b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py#L347) does...
**Is your feature request related to a problem? Please describe.** I'd like to prefill assistant role message content (as outlined here in Claude's official doc: https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/prefill-claudes-response) using `AmazonBedrockGenerator` component **Describe...
We should enable users to use embedding models with the integration, for example text-embedding-004. https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api Came up on discord. Related to https://github.com/deepset-ai/haystack-core-integrations/issues/1530