Haystack Exporter | Respan Docs

Installation

$ pip install respan-exporter-haystack

Classes

RespanConnector

Haystack component that connects pipelines to Respan for tracing.

1 from respan_exporter_haystack import RespanConnector

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Respan API key. Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	API base URL. Falls back to `RESPAN_BASE_URL`.

RespanTracer

Tracing support for Haystack pipeline execution.

1 from respan_exporter_haystack import RespanTracer

RespanGenerator

Gateway component that routes LLM calls through the Respan gateway.

1 from respan_exporter_haystack import RespanGenerator

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Respan API key.
`model`	`str`	—	Model to use (e.g., `"gpt-4o-mini"`).
`base_url`	`str \| None`	`"https://api.respan.ai/api"`	Gateway base URL.

RespanChatGenerator

Chat-specific gateway component.

1 from respan_exporter_haystack import RespanChatGenerator

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Respan API key.
`model`	`str`	—	Model to use.
`base_url`	`str \| None`	`"https://api.respan.ai/api"`	Gateway base URL.

Usage

Tracing

1 from haystack import Pipeline
2 from haystack.components.generators import OpenAIGenerator
3 from respan_exporter_haystack import RespanConnector
4 
5 pipeline = Pipeline()
6 pipeline.add_component("respan", RespanConnector(api_key="your-api-key"))
7 pipeline.add_component("llm", OpenAIGenerator(model="gpt-4o-mini"))
8 pipeline.connect("respan", "llm")
9 
10 result = pipeline.run({"respan": {"prompt": "Tell me a joke"}})

Gateway

1 from haystack import Pipeline
2 from respan_exporter_haystack import RespanGenerator
3 
4 pipeline = Pipeline()
5 pipeline.add_component("llm", RespanGenerator(
6     api_key="your-api-key",
7     model="gpt-4o-mini",
8 ))
9 
10 result = pipeline.run({"llm": {"prompt": "Tell me a joke"}})

Haystack integration guide