NASA-IMPACT / NASA-IMPACT/akd-core
Backlogs:
Open
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 4
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
ToDo
- attach run context dynamically to output schmea object
- something like computed field
- properly typed conversation history
- pydantic schema (lke Role-> ConversationRole -> UserRole, SystemRole, ToolRole, AssistantRole)
- check if litellm supports new response api format? if yes, then standardize multiple format for easy interoperabilit
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files or tests are named. Start by locating the output schema and conversation-history models, then check whether LiteLLM supports the new response API format; done means run context is attached dynamically, conversation roles are typed with the proposed Pydantic hierarchy, and supported formats are standardized.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend-api-design
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100