From 76172511fd1739016895413f6a656e3ffd3c8a32 Mon Sep 17 00:00:00 2001
From: pm390 <56439961+pm390@users.noreply.github.com>
Date: Tue, 14 Jan 2025 21:53:37 +0100
Subject: [PATCH] community: Additional parameters for
 OpenAIAssistantV2Runnable  (#29207)

**Description:** Added Additional parameters that could be useful for
usage of OpenAIAssistantV2Runnable.

This change is thought to allow langchain users to set parameters that
cannot be set using assistants UI
(max_completion_tokens,max_prompt_tokens,parallel_tool_calls) and
parameters that could be useful for experimenting like top_p and
temperature.

This PR originated from the need of using parallel_tool_calls in
langchain, this parameter is very important in openAI assistants because
without this parameter set to False strict mode is not respected by
OpenAI Assistants
(https://platform.openai.com/docs/guides/function-calling#parallel-function-calling).

> Note: Currently, if the model calls multiple functions in one turn
then strict mode will be disabled for those calls.

**Issue:** None
**Dependencies:** openai
---
 .../langchain/agents/openai_assistant/base.py | 48 ++++++++++++++++++-
 1 file changed, 46 insertions(+), 2 deletions(-)

diff --git a/libs/langchain/langchain/agents/openai_assistant/base.py b/libs/langchain/langchain/agents/openai_assistant/base.py
index 63457b63de2c7..148cfc85ab5a3 100644
--- a/libs/langchain/langchain/agents/openai_assistant/base.py
+++ b/libs/langchain/langchain/agents/openai_assistant/base.py
@@ -293,6 +293,12 @@ def invoke(
                 instructions: Additional run instructions.
                 model: Override Assistant model for this run.
                 tools: Override Assistant tools for this run.
+                parallel_tool_calls: Allow Assistant to set parallel_tool_calls
+                    for this run.
+                top_p: Override Assistant top_p for this run.
+                temperature: Override Assistant temperature for this run.
+                max_completion_tokens: Allow setting max_completion_tokens for this run.
+                max_prompt_tokens: Allow setting max_prompt_tokens for this run.
                 run_metadata: Metadata to associate with new run.
             config: Runnable config. Defaults to None.
 
@@ -412,6 +418,12 @@ async def ainvoke(
                 additional_instructions: Appends additional instructions.
                 model: Override Assistant model for this run.
                 tools: Override Assistant tools for this run.
+                parallel_tool_calls: Allow Assistant to set parallel_tool_calls
+                    for this run.
+                top_p: Override Assistant top_p for this run.
+                temperature: Override Assistant temperature for this run.
+                max_completion_tokens: Allow setting max_completion_tokens for this run.
+                max_prompt_tokens: Allow setting max_prompt_tokens for this run.
                 run_metadata: Metadata to associate with new run.
             config: Runnable config. Defaults to None.
             kwargs: Additional arguments.
@@ -514,6 +526,11 @@ def _create_run(self, input: dict) -> Any:
                 "model",
                 "tools",
                 "additional_instructions",
+                "parallel_tool_calls",
+                "top_p",
+                "temperature",
+                "max_completion_tokens",
+                "max_prompt_tokens",
                 "run_metadata",
             )
         }
@@ -527,7 +544,18 @@ def _create_thread_and_run(self, input: dict, thread: dict) -> Any:
         params = {
             k: v
             for k, v in input.items()
-            if k in ("instructions", "model", "tools", "run_metadata")
+            if k
+            in (
+                "instructions",
+                "model",
+                "tools",
+                "parallel_tool_calls",
+                "top_p",
+                "temperature",
+                "max_completion_tokens",
+                "max_prompt_tokens",
+                "run_metadata",
+            )
         }
         run = self.client.beta.threads.create_and_run(
             assistant_id=self.assistant_id,
@@ -651,6 +679,11 @@ async def _acreate_run(self, input: dict) -> Any:
                 "model",
                 "tools",
                 "additional_instructions",
+                "parallel_tool_calls",
+                "top_p",
+                "temperature",
+                "max_completion_tokens",
+                "max_prompt_tokens",
                 "run_metadata",
             )
         }
@@ -664,7 +697,18 @@ async def _acreate_thread_and_run(self, input: dict, thread: dict) -> Any:
         params = {
             k: v
             for k, v in input.items()
-            if k in ("instructions", "model", "tools", "run_metadata")
+            if k
+            in (
+                "instructions",
+                "model",
+                "tools",
+                "parallel_tool_calls",
+                "top_p",
+                "temperature",
+                "max_completion_tokens",
+                "max_prompt_tokens",
+                "run_metadata",
+            )
         }
         run = await self.async_client.beta.threads.create_and_run(
             assistant_id=self.assistant_id,