plano/demos/employee_details_copilot
2024-09-24 14:34:22 -07:00
..
api_server fix demos code (#76) 2024-09-24 14:34:22 -07:00
grafana fix demos code (#76) 2024-09-24 14:34:22 -07:00
prometheus fix demos code (#76) 2024-09-24 14:34:22 -07:00
Bolt-FC-1B-Q3_K_L.model_file fix demos code (#76) 2024-09-24 14:34:22 -07:00
Bolt-FC-1B-Q4_K_M.model_file fix demos code (#76) 2024-09-24 14:34:22 -07:00
bolt_config.yaml fix demos code (#76) 2024-09-24 14:34:22 -07:00
docker-compose.yaml fix demos code (#76) 2024-09-24 14:34:22 -07:00
README.md fix demos code (#76) 2024-09-24 14:34:22 -07:00

Function calling

This demo shows how you can use intelligent prompt gateway to act a copilot for calling the correct proc by capturing the required and optional parametrs from the prompt. This demo assumes you are using ollama running natively. If you want to run ollama running inside docker then please update ollama endpoint in docker-compose file.

Starting the demo

  1. Ensure that submodule is up to date
    git submodule sync --recursive
    
  2. Create .env file and set OpenAI key using env var OPENAI_API_KEY
  3. Start services
    docker compose up
    
  4. Download Bolt-FC model. This demo assumes we have downloaded Bolt-Function-Calling-1B:Q4_K_M to local folder.
  5. If running ollama natively run
    ollama serve
    
  6. Create model file in ollama repository
    ollama create Bolt-Function-Calling-1B:Q4_K_M -f Bolt-FC-1B-Q4_K_M.model_file
    
  7. Navigate to http://localhost:18080/
  8. You can type in queries like "show me the top 5 employees in each department with highest salary"
    • You can also ask follow up questions like "just show the top 2"
  9. To see metrics navigate to "http://localhost:3000/" (use admin/grafana for login)
    • Open up dahsboard named "Intelligent Gateway Overview"
    • On this dashboard you can see reuqest latency and number of requests