traceloop / traceloop/openllmetry

Can't see the workflow trace

Open
#1,994 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
7.4k
Forks
1.1k
Avg merge
8d 14h
Merged PRs (30d)
2

Description

Discussed in https://github.com/traceloop/openllmetry/discussions/1804

Originally posted by eric-easyhealth August 6, 2024
I'm using Haystack2 with latest trackloop 0.26.4, followed the offical guidance to init the traceloop by following code:

Traceloop.init(app_name="app_name", api_key="apikey")

it works perfect and shown me the openai track as following, but how can i enable the workflow track like what is suggested in the quick start document?
PS: i'm using a pipeline in a python class, dummy code as below:

from haystack import Pipeline
from haystack.components.generators.chat import OpenAIChatGenerator

class ChatPipelineViaRAG:
    def __init__(self, api_key:str = '')
        self.retrieve_pipeline = Pipeline()
        self.generator = OpenAIChatGenerator()
        ......
    
    def run(self, messages: List[ChatMessage]) -> dict[str, Any]:
        retrieved_documents = self.retrieve_pipeline.run(parameters...)
        self.messages = process_documents(messages, retrieved_documents)
        return self.generator.run(self.messages)
        

image image

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the Traceloop.init call and the quick start guidance referenced in the issue, then examine how the Haystack Pipeline and OpenAIChatGenerator are used in the example. Determine whether the shown class-based pipeline produces a workflow trace, and verify the expected trace appears after following the documented setup.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
observability
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.