ollama/ollama-python
1
0
Fork 0
mirror of https://github.com/ollama/ollama-python.git synced 2026-07-21 09:05:23 -04:00
Code Issues 101 Packages Projects Releases 10 Wiki Activity

Response + Function Calling on the same model call #180

New Issue
Closed
opened 2026-02-15 16:28:31 -05:00 by yindo · 1 comment
yindo commented 2026-02-15 16:28:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @rsanchezmo on GitHub (Dec 5, 2024).

I was unable to get both a function call and an output on the same model inference (I used llama 3.1:8b). I mean, for a ReAct agent for example, you can ask first to do the THOUGHT process and choose the tools that help you achieve the plan (or the initial steps of it). Then You will feedback the model with the tool output as you did and let the model decide between giving a final answer or replaning (or moving to next step) and call to another set of tools until the agent completed the task.

Is incompatible function calling + generation on the same step in Ollama? meaning thinking a bit then deciding what tools to use? It has demonstrated to be more performant... I saw this example on https://langchain-ai.github.io/langgraph/how-tos/tool-calling/#react-agent and makes me think this is possible and should be possible.

Thanks in advance!

Originally created by @rsanchezmo on GitHub (Dec 5, 2024). I was unable to get both a function call and an output on the same model inference (I used llama 3.1:8b). I mean, for a ReAct agent for example, you can ask first to do the THOUGHT process and choose the tools that help you achieve the plan (or the initial steps of it). Then You will feedback the model with the tool output as you did and let the model decide between giving a final answer or replaning (or moving to next step) and call to another set of tools until the agent completed the task. Is incompatible function calling + generation on the same step in Ollama? meaning thinking a bit then deciding what tools to use? It has demonstrated to be more performant... I saw this example on https://langchain-ai.github.io/langgraph/how-tos/tool-calling/#react-agent and makes me think this is possible and should be possible. Thanks in advance!
yindo closed this issue 2026-02-15 16:28:31 -05:00
yindo commented 2026-02-15 16:28:31 -05:00
Author
Owner
Copy Link
Copy Source

@ParthSareen commented on GitHub (Dec 5, 2024):

Hey! Yeah we only support output at a time. You can still do the same prompt it just won't be outputted in the contents.

@ParthSareen commented on GitHub (Dec 5, 2024): Hey! Yeah we only support output at a time. You can still do the same prompt it just won't be outputted in the contents.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
enhancement
pull-request
Mirrored from GitHub Pull Request
 thinking
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: ollama/ollama-python#180
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?