Haystack-experimental

New Experiments
- Metadata extraction with LLM - [`LLMetadataExtractor`][1]
- Support for tools in [`OllamaChatGenerator`][2] , [`HuggingFaceAPIChatGenerator`][3], [`AnthropicChatGenerator`][4]

[1]: https://github.com/deepset-ai/haystack-experimental/blob/4e1b37aa862147cf3411d9ba9ae72c5d16b5366d/haystack_experimental/components/extractors/llm_metadata_extractor.py
[2]: https://github.com/deepset-ai/haystack-experimental/blob/4e1b37aa862147cf3411d9ba9ae72c5d16b5366d/haystack_experimental/components/generators/ollama/chat/chat_generator.py
[3]: https://github.com/deepset-ai/haystack-experimental/blob/4e1b37aa862147cf3411d9ba9ae72c5d16b5366d/haystack_experimental/components/generators/chat/hugging_face_api.py
[4]: https://github.com/deepset-ai/haystack-experimental/blob/4e1b37aa862147cf3411d9ba9ae72c5d16b5366d/haystack_experimental/components/generators/anthropic/chat/chat_generator.py


**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/compare/v0.2.0...v0.3.0

New experiments
- Tool Calling - [refactored `ChatMessage` dataclass][10], [`Tool` dataclass][4], [refactored `OpenAIChatGenerator`][11], [`ToolInvoker` component][12]
- Memory Components - [`ChatMessageWriter`][5], [`ChatMessageRetriever`][6], [`InMemoryChatMessageStore`][7]
- Document Splitting & Retrieval Techniques - [`Auto-Merging Retriever`][8], [`HierarchicalDocumentSplitter`][9]
- Metadata extraction with LLM - [`LLMetadataExtractor`][13]


[4]: https://github.com/deepset-ai/haystack-experimental/tree/main/haystack_experimental/dataclasses/tool.py
[5]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/writers/chat_message_writer.py
[6]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/retrievers/chat_message_retriever.py
[7]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/chat_message_stores/in_memory.py
[8]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/retrievers/auto_merging_retriever.py
[9]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/splitters/hierarchical_doc_splitter.py
[10]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/dataclasses/chat_message.py
[11]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/generators/chat/openai.py
[12]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/tools/tool_invoker.py
[13]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/extractors/llm_metadata_extractor.py

New Contributors
* dfokina made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/81

**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/compare/v0.1.1...v0.2.0

What's Changed
* Add google colab link to the example harness nb by bilgeyucel in https://github.com/deepset-ai/haystack-experimental/pull/36
* doc: Fix links to API docs and pip packages in RAG eval harness notebook by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/38
* Improve OpenAPITool corner cases handling (missing operationId, servers under paths, etc) by vblagoje in https://github.com/deepset-ai/haystack-experimental/pull/37
* fix: Centralize OpenAPI schema reference resolution by vblagoje in https://github.com/deepset-ai/haystack-experimental/pull/40
* feat: Add telemetry to RAG eval harness by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/42
* docs: Add section about telemetry to the readme by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/44
* docs: add `OpenAPITool` notebook by anakin87 in https://github.com/deepset-ai/haystack-experimental/pull/45

New Contributors
* bilgeyucel made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/36
* anakin87 made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/45

**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/compare/v0.1.0...v0.1.1

New Experiments 🚀
* An [evaluation harness](https://github.com/deepset-ai/haystack-experimental/tree/438ee6bfff75c6a06846a4067189b92191f9a436/haystack_experimental/evaluation/harness) for RAG pipelines
* A [function calling component](https://github.com/deepset-ai/haystack-experimental/blob/438ee6bfff75c6a06846a4067189b92191f9a436/haystack_experimental/components/tools/openai/function_caller.py) for OpenAI.
* An [OpenAPI-based function calling component](https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/tools/openapi/openapi_tool.py) for OpenAI, Cohere and Anthropic.

**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/compare/v0.0.1...v0.1.0

What's Changed
* feat: Implement `PipelinePair` primitive and related utility functions by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/4
* feat: Implement abstract `EvaluationHarness` class by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/5
* refactor: Restructure submodules in `evaluation` by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/6
* feat: Implement `RAGEvaluationHarness` and related classes by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/10
* Add context to the README by masci in https://github.com/deepset-ai/haystack-experimental/pull/7
* fix: Wheel paths for builds by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/12
* fix: Correct parameter name for faithfulness evaluator and fix component names passed to `PipelinePair` by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/13
* adding the OpenAIFunctionCaller by TuanaCelik in https://github.com/deepset-ai/haystack-experimental/pull/14
* feat: Add `ContextRelevanceEvaluator` to RAG eval harness by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/15
* feat: LLM-based Evaluators have `raise_on_Failure=False` by default by davidsbatista in https://github.com/deepset-ai/haystack-experimental/pull/16
* feat: Add ground truth documents and answers to RAG eval run results as inputs by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/17
* chore: Add OpenAIFuntionCaller to catalogue by julian-risch in https://github.com/deepset-ai/haystack-experimental/pull/18
* build: Fetch build version from Git tag by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/19

New Contributors
* masci made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/7
* TuanaCelik made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/14
* davidsbatista made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/16
* julian-risch made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/18

**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/compare/v0.0.1...v0.0.2.dev0

What's Changed
* Add project skeleton by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/1
* build: Fix project structure and version by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/3
* ci: Add workflows by shadeMe in https://github.com/deepset-ai/haystack-experimental/pull/2

New Contributors
* shadeMe made their first contribution in https://github.com/deepset-ai/haystack-experimental/pull/1

**Full Changelog**: https://github.com/deepset-ai/haystack-experimental/commits/v0.0.1