From b5b2d0768137a6cb2a4b9b716e8775eca3c94770 Mon Sep 17 00:00:00 2001
From: Nuno Campos <nuno@langchain.dev>
Date: Wed, 25 Oct 2023 18:03:58 +0100
Subject: [PATCH] Pop max concurrency when recursing (#12281)

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change,
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
---
 libs/langchain/langchain/llms/base.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/libs/langchain/langchain/llms/base.py b/libs/langchain/langchain/llms/base.py
index 44be0f83638..2411afbce88 100644
--- a/libs/langchain/langchain/llms/base.py
+++ b/libs/langchain/langchain/llms/base.py
@@ -294,6 +294,7 @@ class BaseLLM(BaseLanguageModel[str], ABC):
                 inputs[i : i + max_concurrency]
                 for i in range(0, len(inputs), max_concurrency)
             ]
+            config = [{**c, "max_concurrency": None} for c in config]  # type: ignore[misc]
             return [
                 output
                 for batch in batches
@@ -336,10 +337,13 @@ class BaseLLM(BaseLanguageModel[str], ABC):
                 inputs[i : i + max_concurrency]
                 for i in range(0, len(inputs), max_concurrency)
             ]
+            config = [{**c, "max_concurrency": None} for c in config]  # type: ignore[misc]
             return [
                 output
                 for batch in batches
-                for output in await self.abatch(batch, config=config, **kwargs)
+                for output in await self.abatch(
+                    batch, config=config, return_exceptions=return_exceptions, **kwargs
+                )
             ]
 
     def stream(