deepset-ai / deepset-ai/haystack

Extend image support to more components

Open
#9,669 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

P2
Dominant language
Python
Stars
26.6k
Forks
3.2k
Avg merge
1d 3h
Merged PRs (30d)
194

Description

In Haystack 2.16.0, the foundations of image support have been integrated. #8976

We want to bring image support to more components, namely Chat Generators and Embedders.

Notes

  • I already verified that image support works with AzureOpenAIChatGenerator (since inherits from OpenAIChatGenerator)
  • MetaLlamaChatGenerator already works
  • MistralChatGenerator works when used with a multimodal model
  • NvidiaChatGenerator already works
  • OpenRouterChatGenerator already works (tested with Llama 3.2 11B Vision Instruct and Qwen2.5 VL 72B Instruct)
  • STACKITChatGenerator already works (even if they only offer google/gemma-3-27b-it)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the image-support work in #8976 and the existing Chat Generators and Embedders implementations. Identify which listed components still lack image support and the relevant tests; done means the remaining applicable components accept image inputs without regressing existing text use cases.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.