Writer (tracing) | Respan Docs

Writer is an AI content platform with models for text, vision, translation, and knowledge graph workflows.

Set up Respan

Create an account at platform.respan.ai and grab an API key.

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

Example projects

Python examples

Setup

Install packages

$ pip install respan-ai respan-instrumentation-writer writerai

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export WRITER_API_KEY="YOUR_WRITER_API_KEY"

Optional:

$ export RESPAN_BASE_URL="https://api.respan.ai/api"
$ export WRITER_MODEL="palmyra-x5"

Initialize and run

1 import os
2 
3 from respan import Respan, workflow
4 from respan_instrumentation_writer import WriterInstrumentor
5 from writerai import Writer
6 
7 respan = Respan(
8     api_key=os.environ["RESPAN_API_KEY"],
9     base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
10     instrumentations=[WriterInstrumentor()],
11 )
12 
13 client = Writer(api_key=os.environ["WRITER_API_KEY"])
14 
15 
16 @workflow(name="writer_chat.workflow")
17 def run_writer_chat() -> str:
18     completion = client.chat.chat(
19         model=os.getenv("WRITER_MODEL", "palmyra-x5"),
20         messages=[{"role": "user", "content": "Write one line about tracing."}],
21         max_tokens=64,
22     )
23     return completion.choices[0].message.content
24 
25 
26 print(run_writer_chat())
27 respan.flush()
28 respan.shutdown()

View your trace

Open the Traces page and search for workflow name writer_chat.workflow.

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. `WriterInstrumentor()`).
`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()

1 from respan import Respan
2 from respan_instrumentation_writer import WriterInstrumentor
3 
4 respan = Respan(
5     instrumentations=[WriterInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "writer-api", "version": "1.0.0"},
8 )

With propagate_attributes

1 import os
2 
3 from respan import Respan, propagate_attributes
4 from respan_instrumentation_writer import WriterInstrumentor
5 from writerai import Writer
6 
7 respan = Respan(instrumentations=[WriterInstrumentor()])
8 
9 
10 client = Writer(api_key=os.environ.get("WRITER_API_KEY", "local-mock-token"))
11 
12 
13 def run_writer_with_attributes(user_id: str):
14     with propagate_attributes(
15         customer_identifier=user_id,
16         thread_identifier="writer_thread",
17         metadata={"plan": "enterprise"},
18     ):
19         completion = client.chat.chat(
20             model=os.getenv("WRITER_MODEL", "palmyra-x5"),
21             messages=[{"role": "user", "content": "Write one sentence for trace demos."}],
22             max_tokens=32,
23         )
24         print(completion.choices[0].message.content)

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.