Haystack Experimental Components

0.19.0 · active · verified Mon Apr 13

haystack-experimental provides experimental components and features for the Haystack LLM framework (version 2.x). It offers early access to new ideas, integrations, and architectural patterns before they potentially graduate to the main Haystack library. Currently at version 0.19.0, it has a frequent release cadence, often aligning with or preceding Haystack core releases, reflecting its rapidly evolving nature.

Warnings

breaking Components within `haystack-experimental` are volatile. Their APIs are unstable and subject to frequent breaking changes, renaming, or complete removal without prior notice due to their experimental nature.
Fix: Refer to the latest documentation and changelog (`docs.haystack.deepset.ai/reference/experimental-overview`) before upgrading or integrating. Expect to adapt your code frequently.
gotcha Compatibility with the core `haystack-ai` library is tightly coupled. Updates to either `haystack-experimental` or `haystack-ai` can introduce incompatibilities, requiring specific version alignments.
Fix: Always check the release notes of `haystack-experimental` for the compatible `haystack-ai` version. Pin your `haystack-ai` version accordingly.
breaking Python 3.9 support was dropped, requiring Python 3.10 or newer.
Fix: Upgrade your Python environment to 3.10 or higher.
deprecated The `EmbedderBasedDocumentsplitter` component was removed.
Fix: Use standard Haystack DocumentSplitters (e.g., `DocumentSplitter`) or other available experimental text splitting components.
deprecated Human-in-the-Loop (HiTL) related code was removed as it migrated out of `haystack-experimental`.
Fix: Refer to the core Haystack library for current HiTL functionalities, if applicable.

Install

pip install "haystack-experimental[openai]" For LLM usage
pip install haystack-experimental Core experimental components

Imports

Agent

from haystack_experimental.agents.agent import Agent

InMemoryChatMessageStore

from haystack_experimental.memory.in_memory_chat_message_store import InMemoryChatMessageStore

MarkdownHeaderLevelInferrer
```
from haystack_experimental.preprocessors.markdown_header_level_inferrer import MarkdownHeaderLevelInferrer
```
The component moved from 'components.preprocessors' to top-level 'preprocessors' module in recent versions.

Quickstart

This quickstart demonstrates creating and running an experimental Haystack Agent. It uses `OpenAIChatGenerator` (requires `openai` extra) and `PromptBuilder` to respond to a simple query. The `Agent` is a core experimental component for orchestration.

import os
from haystack_experimental.agents.agent import Agent
from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.components.builders.prompt_builder import PromptBuilder

# Ensure your OpenAI API key is set as an environment variable
os.environ['OPENAI_API_KEY'] = os.environ.get('OPENAI_API_KEY', 'sk-...') 

# Initialize LLM and PromptBuilder
llm = OpenAIChatGenerator()
prompt_builder = PromptBuilder(template="{{ query }}")

# Create an experimental Agent
agent = Agent(
    tools=[], # Agents can use tools, but for this quickstart we'll keep it simple
    prompt_builder=prompt_builder,
    llm=llm,
    max_iterations=3,
    debug=True
)

# Run the agent
result = agent.run(query="What is the capital of France?")
print(f"Agent Output: {result.answer}")

view raw JSON →