langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

[PR #1082] [MERGED] DOC: Fix issue in manage-conversation-history.ipynb where unbound model is used for LLM invocations #1877

New Issue
Closed
opened 2026-02-20 17:45:45 -05:00 by yindo · 0 comments
yindo commented 2026-02-20 17:45:45 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/langgraph/pull/1082
Author: @trevor-cyi
Created: 7/21/2024
Status: ✅ Merged
Merged: 7/22/2024
Merged by: @vbarda

Base: main ← Head: fix-bind-model-convo-history

📝 Commits (1)

  • 2befc59 docs: Use bound model in convo history

📊 Changes

1 file changed (+2 additions, -2 deletions)

View changed files

📝 examples/memory/manage-conversation-history.ipynb (+2 -2)

📄 Description

See a link to the published example here.

The example walks through setting up LangGraph with memory. As part of the standard setup, a model is created using ChatAnthropic. Tools are bound to the model and saved in a varliable named bound_model. The original model, stored with a variable named model (without tool access), is then used as part of the call_model function.

Although this does not affect the outcome of the example as written, it is still important to use the correct model as many individuals will pattern after this demo when adding memory in their own applications.

Reproduction Steps

  1. Run the notebook as written, except when providing human input, enter something like "What tools do you have available to you?"
  2. Observe the output, which will likely include hallucinated tool names, and not the search tool as exemplified in the notebook.

Screenshot Example

2024-07-21_20-50

Testing Steps

  1. Pull the code with the commit added as part of this pull request.
  2. Modify the human input to enter something like "What tools do you have available to you?"
  3. Observe the output, which should now include the search tool along with the multi_tool_use tool

Screenshot Example

2024-07-21_20-50_1

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/langgraph/pull/1082 **Author:** [@trevor-cyi](https://github.com/trevor-cyi) **Created:** 7/21/2024 **Status:** ✅ Merged **Merged:** 7/22/2024 **Merged by:** [@vbarda](https://github.com/vbarda) **Base:** `main` ← **Head:** `fix-bind-model-convo-history` --- ### 📝 Commits (1) - [`2befc59`](https://github.com/langchain-ai/langgraph/commit/2befc5915095efe3e92f6728853f42280e5d0d3f) docs: Use bound model in convo history ### 📊 Changes **1 file changed** (+2 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `examples/memory/manage-conversation-history.ipynb` (+2 -2) </details> ### 📄 Description See a link to the published example [here](https://langchain-ai.github.io/langgraph/how-tos/memory/manage-conversation-history/#setup). The example walks through setting up LangGraph with memory. As part of the standard setup, a model is created using `ChatAnthropic`. Tools are bound to the model and saved in a varliable named `bound_model`. The original model, stored with a variable named `model` (_without_ tool access), is then used as part of the `call_model` function. Although this does not affect the outcome of the example as written, it is still important to use the correct model as many individuals will pattern after this demo when adding memory in their own applications. ### Reproduction Steps 1. Run the notebook as written, except when providing human input, enter something like "What tools do you have available to you?" 2. Observe the output, which will likely include hallucinated tool names, and _not_ the `search` tool as exemplified in the notebook. #### Screenshot Example ![2024-07-21_20-50](https://github.com/user-attachments/assets/5fc85cb1-c1ee-4e57-baef-9bc128466bdd) ### Testing Steps 1. Pull the code with the commit added as part of this pull request. 2. Modify the human input to enter something like "What tools do you have available to you?" 4. Observe the output, which should now include the `search` tool along with the `multi_tool_use` tool #### Screenshot Example ![2024-07-21_20-50_1](https://github.com/user-attachments/assets/53dc3569-99bb-49bb-9ae7-285b86f90828) --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-20 17:45:45 -05:00
yindo closed this issue 2026-02-20 17:45:45 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label pull-request
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/langgraph#1877
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?