ccurme

langchain: default to Runnable in MultiQueryRetriever

1

- `llm_chain` becomes `Union[LLMChain, Runnable]` - `.from_llm` creates a runnable tested by verifying that docs/how_to/MultiQueryRetriever.ipynb runs unchanged with sync/async invoke (and that it runs if we specifically instantiate with LLMChain).

Serialization issues with intermediate_steps for AgentExecutor

1

I experimented with a use case in which I initialize an AgentExecutor with an `agent` chain that is a RemoteRunnable. i.e., the client side looks like this: ```python from langchain.agents...

openai[patch]: cache clients

1

https://github.com/langchain-ai/langchain/issues/29925

### Privileged issue - [x] I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here. ### Issue Content We should prefer cached...

### Privileged issue - [x] I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here. ### Issue Content Implement a standalone package...

### Privileged issue - [x] I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here. ### Issue Content If there is an...

Bug: trim_messages and ChatAnthropic token counter with tools

2

### Privileged issue - [x] I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here. ### Issue Content `ChatAnthropic.get_num_tokens_from_messages` uses Anthropic's [token...