I’d like to share my new project for interacting with ChatGPT with using MHBP Scenarios. Scenario is DAG-based definition of steps for prompting ChatGPT, collecting responses, making transformation of such results, creating sub steps
- Store definitions of APIs’ end-points
- Create Scenario with simple UI
- Scenario is supporting DAG ( Directed acyclic graph) execution
- Aggregating results of prompts in final txt document
- Mixing different LLM API in one Scenario
- Application is in form for executable located at github, so no needs to publish your OPENAI_API_KEY anywhere
- Support multi-tenant-based access - many companies, many users
- Deployment can be as desktop application, as SaaS, support different relational databases
Short video of using Scenario with real interaction with ChatGPT API:
- Add Acceptance criteria to each Step which will separate call for ChatGPT for confirmation that Acceptance criteria was met.
- Add a bulk changing of API used in steps of Scenario
I will appreciate any feedback about MHBP Scenario
Free to use for very wide variety of cases - personal, research, non-profit, other cases.
Github - https://github.com/sergmain/metaheuristic
Wiki - https://github.com/sergmain/metaheuristic/wiki