microsoft / microsoft/OmniParser
Suggestion: Add Deepseek V3 API support
Nobody has claimed this yet.
- Dominant language
- Jupyter Notebook
- Stars
- 25.4k
- Forks
- 2.2k
- PR merge metrics
- No merged PRs in 30d
Description
I suggest adding DeepSeek V3 API support to OmniParser. It’s an open-source, 671B MoE model (37B active params) with 60 tokens/sec speed.
This could enhance gradio or omniparserserver with a fast, free alternative to paid APIs like Groq/Anthropic.
Contributor guide
No contributing guide indexed for this repository
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
Start by reviewing the gradio and omniparserserver entry points mentioned in the issue, then determine how existing Groq or Anthropic API support is structured. Done means DeepSeek V3 support is integrated in the appropriate entry point and works as a free alternative to those APIs.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, api
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100