langchain-ai/deepagents
1
0
Fork 0
mirror of https://github.com/langchain-ai/deepagents.git synced 2026-07-22 01:35:28 -04:00
Code Issues 169 Packages Projects Releases 16 Wiki Activity

[PR #64] [CLOSED] feat: research example with openai #436

New Issue
Closed
opened 2026-02-16 09:16:01 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 09:16:01 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/deepagents/pull/64
Author: @WajeehGillani
Created: 8/21/2025
Status: ❌ Closed

Base: master ← Head: feature/openai-example

📝 Commits (1)

  • 046e57e feat: research example with open

📊 Changes

4 files changed (+273 additions, -0 deletions)

View changed files

➕ examples/research_openai/README.md (+78 -0)
➕ examples/research_openai/langgraph.json (+7 -0)
➕ examples/research_openai/requirements.txt (+7 -0)
➕ examples/research_openai/research_agent_openai.py (+181 -0)

📄 Description

Add OpenAI Research Agent Example

What this PR does

Adds a new research agent example that mirrors the existing Anthropic-based research agent but uses OpenAI via LangChain's init_chat_model.

Changes made

  • New example folder: examples/research_openai/
  • New agent file: research_agent_openai.py — OpenAI-powered research agent with same functionality as the Anthropic version
  • Configuration: langgraph.json exposing the graph as research_openai
  • Dependencies: requirements.txt including langchain-openai
  • Documentation: Comprehensive README.md with setup instructions for macOS/Linux

Key Features

  • Uses OpenAI GPT-4o-mini instead of Claude Sonnet 4
  • Maintains identical research workflow: planning, sub-agents (research + critique), virtual filesystem
  • Same tools: Tavily search, file operations, todo management
  • Configurable model settings via init_chat_model

How to Test

  1. Navigate to the example folder:

    cd examples/research_openai/

  2. Set up your .env file with the following:

    OPENAI_API_KEY=your_openai_api_key
TAVILY_API_KEY=your_tavily_api_key

  3. Install dependencies:

    pip install -r requirements.txt

  4. Run the agent:

    langgraph dev
# or
langgraph run research_openai

Why this is Useful

  • Provides an alternative model choice for users who prefer OpenAI
  • Demonstrates how to customize the DeepAgent framework with different LLM providers
  • Maintains feature parity with the existing research example
  • Shows the framework’s flexibility in model integration

🔄 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/deepagents/pull/64 **Author:** [@WajeehGillani](https://github.com/WajeehGillani) **Created:** 8/21/2025 **Status:** ❌ Closed **Base:** `master` ← **Head:** `feature/openai-example` --- ### 📝 Commits (1) - [`046e57e`](https://github.com/langchain-ai/deepagents/commit/046e57e4e8d2a8f590c75eb46fa19a7dff90ac94) feat: research example with open ### 📊 Changes **4 files changed** (+273 additions, -0 deletions) <details> <summary>View changed files</summary> ➕ `examples/research_openai/README.md` (+78 -0) ➕ `examples/research_openai/langgraph.json` (+7 -0) ➕ `examples/research_openai/requirements.txt` (+7 -0) ➕ `examples/research_openai/research_agent_openai.py` (+181 -0) </details> ### 📄 Description # Add OpenAI Research Agent Example ## What this PR does Adds a new research agent example that mirrors the existing Anthropic-based research agent but uses OpenAI via LangChain's `init_chat_model`. --- ## Changes made - **New example folder:** `examples/research_openai/` - **New agent file:** `research_agent_openai.py` — OpenAI-powered research agent with same functionality as the Anthropic version - **Configuration:** `langgraph.json` exposing the graph as `research_openai` - **Dependencies:** `requirements.txt` including `langchain-openai` - **Documentation:** Comprehensive `README.md` with setup instructions for macOS/Linux --- ## Key Features - Uses **OpenAI GPT-4o-mini** instead of Claude Sonnet 4 - Maintains **identical research workflow**: planning, sub-agents (research + critique), virtual filesystem - Same tools: **Tavily search**, file operations, todo management - **Configurable model settings** via `init_chat_model` --- ## How to Test 1. Navigate to the example folder: ```bash cd examples/research_openai/ ``` 2. Set up your `.env` file with the following: ```env OPENAI_API_KEY=your_openai_api_key TAVILY_API_KEY=your_tavily_api_key ``` 3. Install dependencies: ```bash pip install -r requirements.txt ``` 4. Run the agent: ```bash langgraph dev # or langgraph run research_openai ``` --- ## Why this is Useful - Provides an **alternative model choice** for users who prefer OpenAI - Demonstrates how to **customize** the DeepAgent framework with different LLM providers - Maintains **feature parity** with the existing research example - Shows the framework’s **flexibility** in model integration --- <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 2026-02-16 09:16:01 -05:00
yindo closed this issue 2026-02-16 09:16:01 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
MCP
backends
bug
cli
config
customization
deepagents
documentation
external
feature
fix
good first issue
help wanted
integration
internal
invalid
middleware
model
needs investigation
p0
p1
p2
p3
performance
pull-request
Mirrored from GitHub Pull Request
 question
sdk
subagents
unable to reproduce
windows
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/deepagents#436
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?