v0.9.0

🔧 Updates to Experiments

Adding breakpoints to components in a Pipeline

It's now possible to set breakpoints at any component in any pipeline, forcing the pipeline execution to stop before that component runs and generating a JSON file with the complete state of the pipeline before the breakpoint component was run.

Usage Examples

# Setting breakpoints
pipeline.run(
    data={"input": "value"},
    breakpoints={("component_name", 0)},  # Break at the first visit
    debug_path="debug_states/"
)

This will generate a JSON with the complete pipeline state before the next component is run, i.e.: the one receiving the output of the component set in the breakpoint

# Resuming from a saved state
state = Pipeline.load_state("debug_states/component_state.json")
pipeline.run(
    data={"input": "value"},
    resume_state=state
)

🧑‍🍳 See an example notebook here
💬 Share your feedback in this discussion

✅ Adopted Experiments

• chore: Remove Agent after Haystack 2.12 release (#263) @julian-risch
• chore: Remove AutoMergingRetriever after Haystack 2.12 release (#265) @davidsbatista

Other Updates

• Proposal for changing internal working of Agent (#245) @sjrl
• refactor: Streamline super components input and output mapping logic (#243) @sjrl
• refactor: Small updates to Agent. Make pipeline internal, add check for warm_up (#244) @sjrl
• feat: Updates to insertion of values into State (#239) @sjrl
• feat: Add unclassified to output of MultiFileConverter (#240) @julian-risch
• feat: Enhance tool error logs and some refactoring (#235) @sjrl

Full Changelog: v0.8.0...v0.9.0

v0.8.0

🔧 Updates to Experiments

Stream ChatGenerator responses with Agent

The Agent component now allows setting a streaming callback at init and run time. This way, an Agent's response can be streamed in chunks, enabling faster feedback for developers and end users. #233

agent = Agent(chat_generator=chat_generator, tools=[weather_tool])
response = agent.run([ChatMessage.from_user("Hello")], streaming_callback=streaming_callback)

🐛 Bug Fixes

• We fixed a bug that prevented ComponentTool to work with Jinja2-based components (PromptBuilder, ChatPromptBuilder, ConditionalRouter, OutputAdapter). #234
• The Agent component now deserializes Tools with the right class and uses deserialize_tools_inplace. #213 #222

✅ Adopted Experiments

• chore: remove LLMMetadataExtractor by @davidsbatista in #227
• chore: Remove some missed utility functions from previous experiments by @sjrl in #232
• chore: removing async version of InMemoryDocumentStore, DocumentWriter, OpenAIChatGenerator, InMemory Retrievers by @davidsbatista in #220
• chore: remove pipeline experiments by @mathislucka in #214

🛑 Discontinued Experiments

• chore: remove evaluation harness experiment by @julian-risch in #231

Full Changelog: v0.7.0...v0.8.0

v0.7.0

🧪 New Experiments

New Agent component

Agent component enables tool-calling functionality with provider-agnostic chat model support and can be used as a standalone component or within a pipeline.
👉 See the Agent in action: 🧑‍🍳 Build a GitHub Issue Resolver Agent

from haystack.dataclasses import ChatMessage
from haystack.components.websearch import SerperDevWebSearch
from haystack_experimental.tools.component_tool import ComponentTool
from haystack_experimental.components.agents import Agent
from haystack.components.generators.chat import OpenAIChatGenerator

web_tool = ComponentTool(
   component=SerperDevWebSearch(),
)

agent = Agent(
   chat_generator=OpenAIChatGenerator(model="gpt-4o-mini"),
   tools=[web_tool],
   exit_condition="text",
)

result = agent.run(
   messages=[ChatMessage.from_user("Find information about Haystack")]
)

Improved ComponentTool and @tool Decorator

The ComponentTool and @tool decorator are extended for better integration with the new Agent component

New Ready-Made SuperComponents

Introducing new SuperComponents that bundle commonly used components and logic for indexing pipelines: MultiFileConverter, SentenceTransformersDocumentIndexer, DocumentPreprocessor

from haystack_experimental.super_components.converters import MultiFileConverter

# process all common file types (.csv, .docx, .html, .json, .md, .txt, .pdf, .pptx, .xlsx) with one component
converter = MultiFileConverter()
converter.run(sources=["test.txt", "test.pdf"], meta={}) 

What's Changed

• docs: add Supercomponent pydoc, delete outdated by @dfokina in #193
• docs: updating trace comparison tool README.md by @davidsbatista in #195
• chore: Create issue templates for adding, removing, moving an experiment by @julian-risch in #192
• chore: remove OpenSearch from experimental by @anakin87 in #200
• fix: fixing auto-merging tests, removing hard-coded doc ids by @davidsbatista in #202
• chore: add tool related code to prepare Agent PR by @mathislucka in #203
• feat: add file and indexing related super components by @mathislucka in #184
• docs: Add SuperComponent to catalog by @julian-risch in #190
• feat: Introduce Agent by @mathislucka in #175
• docs: add pydoc config for Agent component by @julian-risch in #208
• docs: Notebook for Agent component by @mathislucka in #204
• docs: add MultiFileConverter, SentenceTransformerrsDocumentIndexer, and DocumentPreprocessor to docs by @dfokina in #210

Full Changelog: v0.6.0...v0.7.0

v0.6.0

New Experiments

• New SuperComponent abstraction that allows to wrap any pipeline into a friendly component interface and to create your own super components 1

from haystack_experimental import SuperComponent

# rag_pipeline = basic RAG pipeline with retriever, prompt builder, generator and answer builder components

input_mapping = {
    "search_query": ["retriever.query", "prompt_builder.query", "answer_builder.query"]
}
output_mapping = {
    "answer_builder.answers": "final_answers"
}

wrapper = SuperComponent(
    pipeline=rag_pipeline,
    input_mapping=input_mapping,
    output_mapping=output_mapping
)

result = wrapper.run(search_query="What is the capital of France?")
print(result["final_answers"][0])

• New AsyncPipeline that can schedule components to run concurrently 2

Other Updates:

• Added a debug/tracing script to compare two pipeline runs with the old and new pipeline run logic 3
• Changed LLMMetadaExtractor to use ChatGenerator instead of Generator 4

Full Changelog: v0.5.0...v0.6.0

v0.5.0

New Experiments

• New Pipeline class with new pipeline run logic - Pipeline example

Full Changelog: v0.4.0...v0.5.0

---

🧬 New Pipeline Logic

This release introduces a reimplementation of the pipeline-run logic to resolve multiple issues, improving reliability and performance. These changes will also be included in Haystack 2.10.

Fixed Issues:

1. Exceptions in pipelines with two cycles

   • Pipelines with two cycles sharing an optional (like in PromptBuilder) or a greedy variadic edge (e.g., in BranchJoiner) might raise exceptions. Details here.

2. Incorrect execution in cycles with multiple optional or variadic edges

   • Entry points for cycles were non-deterministic, causing components to run with unexpected inputs or multiple times. This impacted execution time and final outputs.

3. Missing intermediate outputs in cycles

   • Outputs produced within a cycle were overwritten, preventing downstream components from receiving them.

4. Premature execution of lazy variadic components

   • Components like DocumentJoiner sometimes executed before receiving all inputs, leading to repeated partial executions that affected downstream results.

5. Order-sensitive behavior in add_component and connect

   • Some bugs above occurred due to specific orderings of add_component and connect in pipeline creation, causing non-deterministic behavior in cyclic pipelines.

Am I Affected by this Change?

• Non-cyclic pipelines without lazy variadic components:
  No impact—your pipelines should function as before.

• Non-cyclic pipelines with lazy variadic components:
  Check inputs and outputs of components like DocumentJoiner for issues #4 and #5. Use LoggingTracer with content tracing to validate behavior. Component execution order now uses lexicographical sorting; rename upstream components if necessary.

• Pipelines with cycles:
  Review your pipeline outputs as well as the component input and outputs to ensure expected behavior, as you may encounter any of the above issues.

Share your comments in discussion #177

v0.4.0

New Experiments

• AsyncPipeline and async-enabled components - AsyncPipeline example

Full Changelog: v0.3.0...v0.4.0

v0.3.0

New Experiments

• Metadata extraction with LLM - LLMetadataExtractor
• Support for tools in OllamaChatGenerator , HuggingFaceAPIChatGenerator, AnthropicChatGenerator

Full Changelog: v0.2.0...v0.3.0

v0.2.0

New experiments

• Tool Calling - refactored ChatMessage dataclass, Tool dataclass, refactored OpenAIChatGenerator, ToolInvoker component
• Memory Components - ChatMessageWriter, ChatMessageRetriever, InMemoryChatMessageStore
• Document Splitting & Retrieval Techniques - Auto-Merging Retriever, HierarchicalDocumentSplitter
• Metadata extraction with LLM - LLMetadataExtractor

New Contributors

• @dfokina made their first contribution in #81

Full Changelog: v0.1.1...v0.2.0

v0.1.1

What's Changed

• Add google colab link to the example harness nb by @bilgeyucel in #36
• doc: Fix links to API docs and pip packages in RAG eval harness notebook by @shadeMe in #38
• Improve OpenAPITool corner cases handling (missing operationId, servers under paths, etc) by @vblagoje in #37
• fix: Centralize OpenAPI schema reference resolution by @vblagoje in #40
• feat: Add telemetry to RAG eval harness by @shadeMe in #42
• docs: Add section about telemetry to the readme by @shadeMe in #44
• docs: add OpenAPITool notebook by @anakin87 in #45

New Contributors

• @bilgeyucel made their first contribution in #36
• @anakin87 made their first contribution in #45

Full Changelog: v0.1.0...v0.1.1

v0.1.0

New Experiments 🚀

• An evaluation harness for RAG pipelines
• A function calling component for OpenAI.
• An OpenAPI-based function calling component for OpenAI, Cohere and Anthropic.

Full Changelog: v0.0.1...v0.1.0