haystack-core-integrations

haystack-core-integrations copied to clipboard

Improve `OpenSearchDocumentStore.__init__` arguments

3

Closes #671 As explained in the issue, I am proposing to change a bit the arguments that `OpenSearchDocumentStore` accepts. The goal is: 1. First, to allow the user to set...

EdAbati

AmazonBedrockChatGenerator is not working with the Mixtral model

2

**Describe the bug** Calling `run` with the Mixtral model - `mistral.mixtral-8x7b-instruct-v0:1` is failing with the following error message: `Could not inference Amazon Bedrock model mistral.mixtral-8x7b-instruct-v0:1 due: An error occurred (ValidationException)...

vish9812

AmazonBedrockChatGenerator Mistral models cause credentials issue

6

**Describe the bug** When attempting to use Mistral models with the `AmazonBedrockChatGenerator` a 401 unauthenticated error response is returned from huggingface.co as shown below. ```txt None of PyTorch, TensorFlow >=...

chrisk314

Add OptimumEmbedder

2

**Is your feature request related to a problem? Please describe.** Huggin Face's Optimum library provides faster inference through ONNX and TensorRT. This can be used to create blazing fast embedding...

mathislucka

Weaviate: Cannot initialize WeaviateDocumentStore due to connection issue

1

**Describe the bug** This error is returned when I tried to follow the [official documentation](https://haystack.deepset.ai/integrations/weaviate-document-store) to connect to Weaviate managed cluster. Note: The documentation also has an problem, where url...

yip-kl

**Is your feature request related to a problem? Please describe.** I need to use cosine similarity when working with ChromaDB. Currently there's no way to change distance function. **Describe the...

smasyutin

masci

Adding a Haystack example to https://github.com/ollama/ollama/tree/main/examples as a follow up to the conversation here: https://github.com/ollama/ollama/pull/1808#issuecomment-1953409869

masci

**Is your feature request related to a problem? Please describe.** I think that the current implementation of `OpenSearchDocumentStore` should be more specific about which arguments it accepts in the `__init__`...

EdAbati

Fix: max_tokens typo in Mistral Chat

1

ALLOWED_PARAMS has `max_tokens` but generation_kwargs was using `max_gen_len`. Closes Issue : https://github.com/deepset-ai/haystack-core-integrations/issues/741

vish9812