github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8152] LangChain - ChatOLLAMA model - calling tool on every input #30964

New Issue
Closed
opened 2026-04-22 11:00:21 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 11:00:21 -05:00
Owner
Copy Link

Originally created by @Arslan-Mehmood1 on GitHub (Dec 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8152

What is the issue?

llama3.2:1b

llama3.2:3b

llama3.2:1b-instruct-fp16

llama3.1:8b

I've tested above models and all the above models are calling tools even with simple query like 'hi'.

the behavior is same whether binding :

tools_list

openai_format_tools_list

Need help.

Result:


python 1_tool_calling_test.py 
content='' additional_kwargs={} response_metadata={'model': 'llama3.1:8b', 'created_at': '2024-12-18T09:17:37.90843589Z', 'done': True, 'done_reason': 'stop', 'total_duration': 72841245771, 'load_duration': 13778033737, 'prompt_eval_count': 194, 'prompt_eval_duration': 50723000000, 'eval_count': 22, 'eval_duration': 8337000000, 'message': Message(role='assistant', content='', images=None, tool_calls=[ToolCall(function=Function(name='tavily_search_results_json', arguments={'query': 'current events'}))])} id='run-8931e574-9297-4ce9-93f1-54d00ce8c413-0' tool_calls=[{'name': 'tavily_search_results_json', 'args': {'query': 'current events'}, 'id': '82754a8a-619b-4a1e-85d3-cb767d4c6a9f', 'type': 'tool_call'}] usage_metadata={'input_tokens': 194, 'output_tokens': 22, 'total_tokens': 216} 


[{'name': 'tavily_search_results_json', 'args': {'query': 'current events'}, 'id': '82754a8a-619b-4a1e-85d3-cb767d4c6a9f', 'type': 'tool_call'}]

Code For testing:


from typing import List
from dotenv import load_dotenv, find_dotenv
load_dotenv(find_dotenv())
from langchain_core.tools import tool
from langchain_ollama import ChatOllama
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.utils.function_calling import convert_to_openai_tool

# @tool
# def web_search_tool(web_query: str) -> str:
#     """
#     Use this tool only when you need to use web search in order to find an answer for user.
#     Args:
#         web_query (str) : the query for web search
    
#     """
#     search = TavilySearchResults()
#     results = search.invoke(query)
#     return results

web_search_tool = TavilySearchResults()

tools_list = [web_search_tool]
openai_format_tools_list = [convert_to_openai_tool(f) for f in tools_list]

llm = ChatOllama(model="llama3.1:8b", temperature=0).bind_tools(tools_list)

result = llm.invoke("Hi, how are you?")

print(result,"\n\n")
print(result.tool_calls)

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.5.1

Originally created by @Arslan-Mehmood1 on GitHub (Dec 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8152 ### What is the issue? llama3.2:1b llama3.2:3b llama3.2:1b-instruct-fp16 llama3.1:8b I've tested above models and all the above models are calling tools even with simple query like 'hi'. the behavior is same whether binding : tools_list openai_format_tools_list Need help. Result: ``` python 1_tool_calling_test.py content='' additional_kwargs={} response_metadata={'model': 'llama3.1:8b', 'created_at': '2024-12-18T09:17:37.90843589Z', 'done': True, 'done_reason': 'stop', 'total_duration': 72841245771, 'load_duration': 13778033737, 'prompt_eval_count': 194, 'prompt_eval_duration': 50723000000, 'eval_count': 22, 'eval_duration': 8337000000, 'message': Message(role='assistant', content='', images=None, tool_calls=[ToolCall(function=Function(name='tavily_search_results_json', arguments={'query': 'current events'}))])} id='run-8931e574-9297-4ce9-93f1-54d00ce8c413-0' tool_calls=[{'name': 'tavily_search_results_json', 'args': {'query': 'current events'}, 'id': '82754a8a-619b-4a1e-85d3-cb767d4c6a9f', 'type': 'tool_call'}] usage_metadata={'input_tokens': 194, 'output_tokens': 22, 'total_tokens': 216} [{'name': 'tavily_search_results_json', 'args': {'query': 'current events'}, 'id': '82754a8a-619b-4a1e-85d3-cb767d4c6a9f', 'type': 'tool_call'}] ``` Code For testing: ``` from typing import List from dotenv import load_dotenv, find_dotenv load_dotenv(find_dotenv()) from langchain_core.tools import tool from langchain_ollama import ChatOllama from langchain_community.tools.tavily_search import TavilySearchResults from langchain_core.utils.function_calling import convert_to_openai_tool # @tool # def web_search_tool(web_query: str) -> str: # """ # Use this tool only when you need to use web search in order to find an answer for user. # Args: # web_query (str) : the query for web search # """ # search = TavilySearchResults() # results = search.invoke(query) # return results web_search_tool = TavilySearchResults() tools_list = [web_search_tool] openai_format_tools_list = [convert_to_openai_tool(f) for f in tools_list] llm = ChatOllama(model="llama3.1:8b", temperature=0).bind_tools(tools_list) result = llm.invoke("Hi, how are you?") print(result,"\n\n") print(result.tool_calls) ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.1
GiteaMirror added the bug label 2026-04-22 11:00:22 -05:00
GiteaMirror commented 2026-04-22 11:00:24 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 18, 2024):

#6127

<!-- gh-comment-id:2550892170 --> @rick-github commented on GitHub (Dec 18, 2024): #6127
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#30964
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?