How deepika68/ai-agents works
This is a small command-line research agent: a user submits a question, the entry point retrieves web results, passes the resulting context to an LLM, and prints the answer. The implementation uses DuckDuckGo search and Groq; the README also mentions Gemini, but the sampled source shows no Gemini integration. A separate prompt file defines research-assistant guidance, though the entry point and LLM module do not use it. The graph reflects only relationships visible in the excerpts.
Main entry points: main.py CLI entry point · tools.py Web search · llm.py Answer generation
Components 7
CLI workflow
- CLI entry point
main.py
Web retrieval
- Web search
tools.py
Answer generation
- Answer generation
llm.py - Research prompt
prompts.py
Other components
- Question asker
- DuckDuckGo
- Groq API
Connections 7
- Question asker → CLI entry point: asks question
main.py - CLI entry point → Web search: queries
main.py - Web search → DuckDuckGo: searches web
tools.py - Web search → CLI entry point: returns context
main.py - CLI entry point → Answer generation: requests answer
main.py - Answer generation → Groq API: sends completion
llm.py - Answer generation → CLI entry point: returns answer
main.py