From f4568fe0c609f8a4a832571fc927349c158f04f0 Mon Sep 17 00:00:00 2001
From: Nuno Campos <nuno@langchain.dev>
Date: Tue, 2 Apr 2024 16:40:27 -0700
Subject: [PATCH] core: BaseChatModel modify chat message before passing to
 run_manager (#19939)

Thank you for contributing to LangChain!

- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
  - Example: "community: add foobar LLM"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!


- [ ] **Add tests and docs**: 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/docs/integrations` directory.


- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

Additional guidelines:
- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to pyproject.toml files (even optional
ones) unless they are required for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.
- If you are adding something to community, do not re-import it in
langchain.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---
 .../language_models/chat_models.py               | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/libs/core/langchain_core/language_models/chat_models.py b/libs/core/langchain_core/language_models/chat_models.py
index daf6aeb3a736b..7040900aeef78 100644
--- a/libs/core/langchain_core/language_models/chat_models.py
+++ b/libs/core/langchain_core/language_models/chat_models.py
@@ -221,12 +221,12 @@ def stream(
             generation: Optional[ChatGenerationChunk] = None
             try:
                 for chunk in self._stream(messages, stop=stop, **kwargs):
-                    run_manager.on_llm_new_token(
-                        cast(str, chunk.message.content), chunk=chunk
-                    )
                     if chunk.message.id is None:
                         chunk.message.id = f"run-{run_manager.run_id}"
                     chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
+                    run_manager.on_llm_new_token(
+                        cast(str, chunk.message.content), chunk=chunk
+                    )
                     yield chunk.message
                     if generation is None:
                         generation = chunk
@@ -293,12 +293,12 @@ async def astream(
                 stop=stop,
                 **kwargs,
             ):
-                await run_manager.on_llm_new_token(
-                    cast(str, chunk.message.content), chunk=chunk
-                )
                 if chunk.message.id is None:
                     chunk.message.id = f"run-{run_manager.run_id}"
                 chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
+                await run_manager.on_llm_new_token(
+                    cast(str, chunk.message.content), chunk=chunk
+                )
                 yield chunk.message
                 if generation is None:
                     generation = chunk
@@ -610,13 +610,13 @@ def _generate_with_cache(
         ):
             chunks: List[ChatGenerationChunk] = []
             for chunk in self._stream(messages, stop=stop, **kwargs):
+                chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                 if run_manager:
                     if chunk.message.id is None:
                         chunk.message.id = f"run-{run_manager.run_id}"
                     run_manager.on_llm_new_token(
                         cast(str, chunk.message.content), chunk=chunk
                     )
-                chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                 chunks.append(chunk)
             result = generate_from_stream(iter(chunks))
         else:
@@ -691,13 +691,13 @@ async def _agenerate_with_cache(
         ):
             chunks: List[ChatGenerationChunk] = []
             async for chunk in self._astream(messages, stop=stop, **kwargs):
+                chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                 if run_manager:
                     if chunk.message.id is None:
                         chunk.message.id = f"run-{run_manager.run_id}"
                     await run_manager.on_llm_new_token(
                         cast(str, chunk.message.content), chunk=chunk
                     )
-                chunk.message.response_metadata = _gen_info_and_msg_metadata(chunk)
                 chunks.append(chunk)
             result = generate_from_stream(iter(chunks))
         else: