mathislucka

**Is your feature request related to a problem? Please describe.** After adding AsyncPipeline in Haystack 2.10 we should add a run_async method to each ChatGenerator that is IO-bound. **ChatGenerators**

**Is your feature request related to a problem? Please describe.** As we released AsyncPipeline in 2.10, we should add run_async methods for all relevant retrievers. --- By @anakin87: When adding...

**Describe the bug** When using `AsyncPipeline.run` we get a RunTimeError because it calls `asyncio.run` internally which fails because Jupyter is already running an event-loop. **Error message** `RuntimeError: asyncio.run() cannot be...

Component protocol not correctly recognized by PyCharm anymore

1

**Describe the bug** [This PR](https://github.com/deepset-ai/haystack/pull/9329) leads to type errors with the PyCharm linter (2024.3.5 Professional Edition). When using `Pipeline.add_component` PyCharm flags a typing issue (`Expected type 'Component', got 'ChatPromptBuilder' instead`)....

Agent should support prompt caching

7

**Is your feature request related to a problem? Please describe.** In Agents with many tool calls, input tokens can accumulate quickly. Prompt caching (when supported by the LLM) can heavily...

Chat generators or Agent should work intelligently around rate limits

5

**Is your feature request related to a problem? Please describe.** At the hackathon today we ran into quite a few rate limit issues with the OpenAI and Anthropic API. The...

Introduce consistent handling of `warm_up` for components

2

This issue was brought up by @davidsbatista during the review of We defer time-consuming or resource expensive operations when initializing components so that loading of a pipeline to validate it...