apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-06 14:22:51 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
plano/demos/employee_details_copilot
History
Adil Hafeez dbb8f87787
update path for arch_config.yaml file (#107)
2024-10-01 13:28:53 -07:00
..
api_server Rename bolt_config to arch_config (#100) 2024-09-30 18:47:35 -07:00
grafana fix demos code (#76) 2024-09-24 14:34:22 -07:00
prometheus Rename bolt_config to arch_config (#100) 2024-09-30 18:47:35 -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 Added Float type to the function parameter values (#77) 2024-09-25 13:29:20 -07:00
docker-compose.yaml update path for arch_config.yaml file (#107) 2024-10-01 13:28:53 -07:00
README.md Added Float type to the function parameter values (#77) 2024-09-25 13:29:20 -07:00

README.md

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. Create .env file and set OpenAI key using env var OPENAI_API_KEY
  2. Start services 
    docker compose up
  3. Download Bolt-FC model. This demo assumes we have downloaded Bolt-Function-Calling-1B:Q4_K_M to local folder.
  4. If running ollama natively run 
    ollama serve
  5. Create model file in ollama repository 
    ollama create Bolt-Function-Calling-1B:Q4_K_M -f Bolt-FC-1B-Q4_K_M.model_file
  6. Navigate to http://localhost:18080/
  7. 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"
  8. 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