Langflow | Respan Docs

Langflow is a visual framework by DataStax for building multi-agent and RAG applications. It provides a drag-and-drop interface for composing LLM pipelines with components for models, prompts, tools, and data sources. Built on LangChain, every flow execution is auto-traced by Respan, with full observability over component runs and LLM calls — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Langflow is built on LangChain, so tracing uses the LangChain instrumentor.

Install packages

$ pip install respan-ai openinference-instrumentation-langchain langflow

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from langflow.load import run_flow_from_json
2 from respan import Respan
3 from openinference.instrumentation.langchain import LangChainInstrumentor
4 
5 respan = Respan(instrumentations=[LangChainInstrumentor()])
6 
7 result = run_flow_from_json(
8     flow="path/to/your/flow.json",
9     input_value="What is the meaning of life?",
10 )
11 print(result)
12 respan.flush()

View your trace

Open the Traces page to see your Langflow workflow with component-level operations, LLM calls, and pipeline execution.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `LangChainInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from openinference.instrumentation.langchain import LangChainInstrumentor
3 
4 respan = Respan(
5     instrumentations=[LangChainInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "langflow-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from langflow.load import run_flow_from_json
2 from respan import Respan, propagate_attributes
3 from openinference.instrumentation.langchain import LangChainInstrumentor
4 
5 respan = Respan(instrumentations=[LangChainInstrumentor()])
6 
7 def handle_request(user_id: str, question: str):
8     with propagate_attributes(
9         customer_identifier=user_id,
10         thread_identifier="conv_abc_123",
11         metadata={"plan": "pro"},
12     ):
13         result = run_flow_from_json(flow="flow.json", input_value=question)
14         print(result)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.