le-codeur-rapide comments

Results 4 comments of


                                            le-codeur-rapide

The max_concurrency parameter in llm.abatch() is not working as expected

From my understanding, rate limit errors are from the server side. If you run request to the servers in parallel, you will have a even higher rate. Have you tried...

Returning `Command` with `goto` attribute in a graph with >= 3 total graph depth results in `langgraph.errors.ParentCommand` error

Hello everyone ! I was looking at this issue also, it looks like there might be an issue with how the `checkpoint_ns` is handle when ParentCommand is raised: I found...

create_agent In "astream" with stream_mode="messages" does not output tokens incrementally.

Hello @nswsnb I ran your code and it worked as expected: I just replaced `print(token.content)` by `print(token.content + "|", end="")` and got output: ``` |Hello|!| I'm| an| AI| language| model|...

AttributeError in streaming when InMemorySaver is used

Hello @inancsevinc Looking at the docstring example of the `InMemorySaver` : [link to code](https://github.com/langchain-ai/langgraph/blob/d45f52ab0cac3d036c960cb344095294b537c3fe/libs/checkpoint/langgraph/checkpoint/memory/__init__.py#L60): You don't need to do ```python async with checkpointer as entered: ...... app = graph.compile(checkpointer=entered) ```...