Skip to content

issues Search Results · repo:langchain-ai/langgraph-swarm-py language:Python

Filter by

50 results
 (59 ms)

50 results

inlangchain-ai/langgraph-swarm-py (press backspace or delete to remove)

Hello, I m currently trying to add evals to my swarms to ease their maintenance using the langchain-ai/agentevals library, I faced against this implementation where they explain the Graph trajectory LLM-as-judge ...
  • martin-santiago
  • Opened 
    2 days ago
  • #80

Does this implementation have advantages compared to pure Swarm ?
  • dizhenx
  • 2
  • Opened 
    9 days ago
  • #79

Hi!, I have a fastAPI project with an endpoint that runs a swarm, I started a few weeks ago following the tutorial and I ve had great results with my agents!, but today I faced a big problem in production, ...
  • martin-santiago
  • 4
  • Opened 
    9 days ago
  • #78

Hi @vbarda Vadym. Is it possible to run a swarm for a long time? I mean, for a long time, over days. Something like daemons. If so, is it possible to: - Add and remove agents to the swarm dynamically? ...
  • leo-gan
  • 1
  • Opened 
    13 days ago
  • #77

I ve implemented a swarm with 3 agents and they are working great, I ve created a custom handoff tool to update the PARENT.state through the handoffs and it works fine, I have one problem tho, I have one ...
  • martin-santiago
  • 2
  • Opened 
    29 days ago
  • #70

If there are multiple tool calls in LLM response, and there is handoff tool in it, though all tools will be executed, only result of handoff tool will return, results of all other tools just disappear. ...
  • xinwo
  • 1
  • Opened 
    29 days ago
  • #69

In the sample here, active agent is in the result of invoke. How to get active agent in streaming mode?
  • sei-li-miidas
  • 2
  • Opened 
    on Apr 16
  • #68

I managed to create the swarm with three basic agents as follows: client_data_retriever_agent = create_react_agent( model, [ create_handoff_tool(agent_name= introduction_and_doubts_agent ...
  • martin-santiago
  • 1
  • Opened 
    on Apr 15
  • #67

In my implementation it would be convenient that the agent passes a summary or explanation of the task that the handoffed agent has to solve. For that I want to know how can you pass to the handoff tool ...
  • rorro6787
  • 2
  • Opened 
    on Apr 15
  • #66

Hi, The examples show the llm/model creation hardcoded before being assigend to create_react_agent calls versus being able to set using a runtime configruable. In my wotk, I always like to set the model ...
  • designzoo-adrian
  • 2
  • Opened 
    on Apr 14
  • #65
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub