langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 12:25:55 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #1290] [langchain]: is there equivalent to the create_tool_calling_agent in langchain@1.0? #188

New Issue
Open
opened 2026-02-17 17:19:22 -05:00 by yindo · 5 comments
yindo commented 2026-02-17 17:19:22 -05:00
Owner
Copy Link
Copy Source

Originally created by @fathurwithyou on GitHub (Nov 5, 2025).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/1290

Type of issue

question

Language

Python

Description

Previously, I used create_tool_calling_agent for developing a filling form agent, it produces amazing minimal latency because of parallelization. The current problem I face right now, langchain v1 reduces the interface to create_agent interface that uses reAct technique, and it does tool calling sequentially. The question: Is there any equivalent code to reproduce create_tool_calling_agent in langchain@1.0.

Originally created by @fathurwithyou on GitHub (Nov 5, 2025). Original GitHub issue: https://github.com/langchain-ai/docs/issues/1290 ### Type of issue question ### Language Python ### Description Previously, I used create_tool_calling_agent for developing a filling form agent, it produces amazing minimal latency because of parallelization. The current problem I face right now, langchain v1 reduces the interface to create_agent interface that uses reAct technique, and it does tool calling sequentially. The question: Is there any equivalent code to reproduce create_tool_calling_agent in langchain@1.0.
yindo added the langchainexternal labels 2026-02-17 17:19:22 -05:00
yindo commented 2026-02-17 17:19:22 -05:00
Author
Owner
Copy Link
Copy Source

@fathurwithyou commented on GitHub (Nov 5, 2025):

This question is just for curiosity, since we can use it on langchain_classic, but did you guys think about other techniques in v1.0, not only ReAct?

@fathurwithyou commented on GitHub (Nov 5, 2025): This question is just for curiosity, since we can use it on langchain_classic, but did you guys think about other techniques in v1.0, not only ReAct?
yindo commented 2026-02-17 17:19:22 -05:00
Author
Owner
Copy Link
Copy Source

@alexkeyme commented on GitHub (Nov 5, 2025):

Which functionality are you missing in create_agent? Because that would've been my suggestion, too...

@alexkeyme commented on GitHub (Nov 5, 2025): Which functionality are you missing in create_agent? Because that would've been my suggestion, too...
yindo commented 2026-02-17 17:19:22 -05:00
Author
Owner
Copy Link
Copy Source

@Astroa7m commented on GitHub (Nov 28, 2025):

I think create_agent doesn't support parallel tool execution, like you said it uses a sequential ReAct loop. So I guess you have the classic, create custom middleware to intercept, or switch langgraph to achieve tool parallel exec

@Astroa7m commented on GitHub (Nov 28, 2025): I think create_agent doesn't support parallel tool execution, like you said it uses a sequential ReAct loop. So I guess you have the classic, create custom middleware to intercept, or switch langgraph to achieve tool parallel exec
yindo commented 2026-02-17 17:19:22 -05:00
Author
Owner
Copy Link
Copy Source

@fathurwithyou commented on GitHub (Dec 3, 2025):

I think create_agent doesn't support parallel tool execution, like you said it uses a sequential ReAct loop. So I guess you have the classic, create custom middleware to intercept, or switch langgraph to achieve tool parallel exec

Yup, this is what they miss, parallel tool execution is something needed.

@fathurwithyou commented on GitHub (Dec 3, 2025): > I think create_agent doesn't support parallel tool execution, like you said it uses a sequential ReAct loop. So I guess you have the classic, create custom middleware to intercept, or switch langgraph to achieve tool parallel exec Yup, this is what they miss, parallel tool execution is something needed.
yindo commented 2026-02-17 17:19:22 -05:00
Author
Owner
Copy Link
Copy Source

@alexkeyme commented on GitHub (Dec 4, 2025):

Have you tried using multiple create_agents in parallel? Haven't done that myself, just an idea... you'd probably need one supervisor which then spawns sub agents.

Or, try deep agents which allows to pass in sub agents: https://github.com/langchain-ai/deepagents/tree/master

@alexkeyme commented on GitHub (Dec 4, 2025): Have you tried using multiple create_agents in parallel? Haven't done that myself, just an idea... you'd probably need one supervisor which then spawns sub agents. Or, try deep agents which allows to pass in sub agents: https://github.com/langchain-ai/deepagents/tree/master
yindo changed title from [langchain]: is there equivalent to the create_tool_calling_agent in langchain@1.0? to [GH-ISSUE #1290] [langchain]: is there equivalent to the create_tool_calling_agent in langchain@1.0? 2026-06-05 17:25:33 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label external langchain
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: langchain-ai/docs#188
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?