agent-lightning
agent-lightning copied to clipboard
microsoft
The absolute trainer to light up AI agents.
This pull request implements a `SqlLightningStore` which uses a SQL database for persistent storage and online querying of rollouts, attempts, and spans. ## Key Changes The main addition is in...
Great job!! I have a question about the source code logic that I would like to ask. Judging from a few examples, it seems that the agent directly returns a...
When running the RAG training script train.sh in the example folder, the following error occurs: 2025-11-07 08:43:54,784 INFO worker.py:1832 -- Connecting to existing Ray cluster at address: 172.17.0.2:6379... 2025-11-07 08:43:54,795...
In examples/spider/sql_agent, on line 259, the function definition `def truncate_execuion(self, execution: str) -> str:` was missing a “t” in the name. I corrected it to truncate_execution, and also fixed two...
In agent lightning, we collect all transitions and use `balance_batch` to reorder them for maximized efficiency. This practice might have performance issues. I will try to investigate.
Thank you for your work. I am running the spider and calc_x tasks, and after specifying a local model, I consistently encounter the errors "No deployments available for selected model"...
fix issue https://github.com/microsoft/agent-lightning/issues/262 for anthropic api via `agentlightning.LLMProxy` unit test result: ```bash (agentlightning) [email protected]@GCRAZGDL1513:~/code/local_agl$ pytest -v tests/llm_proxy/test_llm_proxy_gpu.py ================================================================================= test session starts ================================================================================= platform linux -- Python 3.12.3, pytest-8.4.2, pluggy-1.6.0 --...
