[1]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/agents/agent.py
[2]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/core/super_component/super_component.py
[4]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/retrievers/auto_merging_retriever.py
[5]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/splitters/hierarchical_doc_splitter.py
[6]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/chat_message_stores/in_memory.py
[7]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/retrievers/chat_message_retriever.py
[8]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/writers/chat_message_writer.py

### Adopted experiments
| Name | Type | Final release |
|----------------------------------------------------------------------------------------|------------------------------------------|---------------|
| `ChatMessage` refactoring; `Tool` class; tool support in ChatGenerators; `ToolInvoker` | Tool Calling support | 0.4.0 |
| `AsyncPipeline`; `Pipeline` bug fixes and refactoring | AsyncPipeline execution | 0.7.0 |
| `LLMMetadataExtractor` | Metadata extraction with LLM | 0.7.0 |
| `Auto-Merging Retriever` & `HierarchicalDocumentSplitter` | Document Splitting & Retrieval Technique | 0.8.0 |

### Discontinued experiments

| Name | Type | Final release | Cookbook |
|------------------------|----------------------------|---------------|------------------------------------------------------------------------------------------------------------------------------------------|
| `OpenAIFunctionCaller` | Function Calling Component | 0.3.0 | None |
| `OpenAPITool` | OpenAPITool component | 0.3.0 | [Notebook](https://github.com/deepset-ai/haystack-experimental/blob/fe20b69b31243f8a3976e4661d9aa8c88a2847d2/examples/openapitool.ipynb) |
| `EvaluationHarness` | Evaluation orchestrator | 0.7.0 | None |

## Usage

Experimental new features can be imported like any other Haystack integration package:

```python
from haystack.dataclasses import ChatMessage
from haystack_experimental.components.generators import FoobarGenerator

c = FoobarGenerator()
c.run([ChatMessage.from_user("What's an experiment? Be brief.")])
```

Experiments can also override existing Haystack features. For example, users can opt into an experimental type of
`Pipeline` by just changing the usual import:

```python
# from haystack import Pipeline
from haystack_experimental import Pipeline

pipe = Pipeline()
# ...
pipe.run(...)
```

Some experimental features come with example notebooks and resources that can be found in the [`examples` folder](https://github.com/deepset-ai/haystack-experimental/tree/main/examples).

## Documentation

Documentation for `haystack-experimental` can be found [here](https://docs.haystack.deepset.ai/reference/experimental-data-classes-api).

## Implementation

Experiments should replicate the namespace of the core package. For example, a new generator:

```python
# in haystack_experimental/components/generators/foobar.py

from haystack import component

@component
class FoobarGenerator:
...

```

When the experiment overrides an existing feature, the new symbol should be created at the same path in the experimental
package. This new symbol will override the original in `haystack-ai`: for classes, with a subclass and for bare
functions, with a wrapper. For example:

```python
# in haystack_experiment/src/haystack_experiment/core/pipeline/pipeline.py

from haystack.core.pipeline import Pipeline as HaystackPipeline

class Pipeline(HaystackPipeline):
# Any new experimental method that doesn't exist in the original class
def run_async(self, inputs) -> Dict[str, Dict[str, Any]]:
...

# Existing methods with breaking changes to their signature, like adding a new mandatory param
def to_dict(new_param: str) -> Dict[str, Any]:
# do something with the new parameter
print(new_param)
# call the original method
return super().to_dict()

```

## Contributing

Direct contributions to `haystack-experimental` are not expected, but Haystack maintainers might ask contributors to move pull requests that target the [core repository](https://github.com/deepset-ai/haystack) to this repository.

## Telemetry