Skip to content

Conversation

@wongzhenhao
Copy link
Contributor

No description provided.

embedding_serving = LocalModelLLMServing_vllm(hf_model_name_or_path="/mnt/public/data/lh/models/hub/gte-Qwen2-7B-instruct", vllm_max_tokens=8192)
# embedding_serving = LocalModelLLMServing_vllm(hf_model_name_or_path="/mnt/public/data/lh/models/hub/gte-Qwen2-7B-instruct", vllm_max_tokens=8192)
embedding_serving = APILLMServing_request(
api_url="http://123.129.219.111:3000/v1/embeddings",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

鱼叉 url换成别的

@wongzhenhao
Copy link
Contributor Author

Besides, llm API serving now support embedding model, eg. OpenAI's text-embedding-ada-002, text-embedding-3-small, et al.

@wongzhenhao wongzhenhao changed the title [Update] AgenticRAG pipeline fully support API request [Update] APILLMServing_request now support embedding model & AgenticRAG pipeline fully support API request Jul 11, 2025
Copy link
Collaborator

@SunnyHaze SunnyHaze left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me.

@SunnyHaze SunnyHaze merged commit a7dcdeb into OpenDCAI:main Jul 11, 2025
9 checks passed
wongzhenhao added a commit to wongzhenhao/DataFlow that referenced this pull request Oct 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants