https://github.com/ka25van/langgraph_multiagent_tryout
https://github.com/ka25van/langgraph_multiagent_tryout
agents express javascript langchain langgraph llm nodejs ollama postman
Last synced: 7 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/ka25van/langgraph_multiagent_tryout
- Owner: ka25van
- Created: 2025-07-04T10:45:43.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2025-07-04T11:44:40.000Z (9 months ago)
- Last Synced: 2025-07-04T12:58:20.516Z (9 months ago)
- Topics: agents, express, javascript, langchain, langgraph, llm, nodejs, ollama, postman
- Language: JavaScript
- Homepage:
- Size: 23.4 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
User Input: "Hello! Can you help me with programming?"
What Happens:
🧠Router sees "Hello" → routes to Greeting Agent; if 'help' it will route to HelpAgent orelse it will route to Chat Agent
👋 Greeting Agent creates a warm, welcoming response
🦙 Llama 3.2 generates: "Hello! Welcome! I'd be happy to help you with programming. What specific programming topic or challenge are you working on?"
📤 User gets a personalized, contextually appropriate response
This LangGraph project is like having multiple AI personalities that automatically choose the best one for each situation, all powered by a single local AI model llama3.2.
(Suggestion:-Run a better model configured from cloud for fater response generation rather than using default ollama url.)
These are few of the examples that i tested in Postman:-
/batch:- Can ask multiple questions
/chat:- Can ask one question.
You can cut short the response length in the hyperparameter or in the prompt too.