mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-29 03:57:36 +08:00
4783ce9951
### What problem does this PR solve? IDK how to implement **`Ollama`** on #14580 but it's totally wrong. This is the rewrite version for **`Ollama`** **Verified from CLI** ``` # Embed RAGFlow(user)> embed text 'what is rag' 'who are you' with 'nomic-embed-text:latest@test12@ollama' dimension 1024; +-----------+-------+ | dimension | index | +-----------+-------+ | 768 | 0 | | 768 | 1 | +-----------+-------+ # Chat RAGFlow(user)> think chat with 'qwen3:0.6b@test12@ollama' message 'who r u' Thinking: Okay, the user asked, "Who r u?" I need to respond appropriately. First, I should acknowledge their question. Since I'm an AI, I don't have a physical form, but I can confirm that I'm a large language model. I should keep the response friendly and offer help. Let me make sure I'm not making up any information and that the response is natural. Also, I should check for any typos and ensure clarity. Alright, that should cover it. Answer: I'm an AI language model, and I don't have a physical form. However, I can tell you that I'm designed to assist with questions and tasks. How can I help you today? Time: 2.914285 RAGFlow(user)> stream think chat with 'qwen3:0.6b@test12@ollama' message 'who r u' Thinking: , the user asked, "Who are you?" I need to respond appropriately. Since I'm an AI assistant, I should mention that I don't have a physical form or a mind. I should also clarify that I can help with various tasks like answering questions or providing information. It's important to keep the response friendly and informative while maintaining the correct tone. Answer: don't have a physical form or a mind, but I'm here to help with your questions or tasks! What can I do for you today? Time: 1.740047 # LisyModels RAGFlow(user)> list supported models from 'ollama' 'test12' +-------------------------+ | model_name | +-------------------------+ | nomic-embed-text:latest | | qwen3:0.6b | +-------------------------+ ``` ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) - [x] Refactoring
13 lines
260 B
JSON
13 lines
260 B
JSON
{
|
|
"name": "xinference",
|
|
"url_suffix": {
|
|
"chat": "v1/chat/completions",
|
|
"embedding": "v1/embeddings",
|
|
"models": "v1/models",
|
|
"rerank": "v1/rerank",
|
|
"asr": "v1/audio/transcriptions",
|
|
"tts": "v1/audio/speech"
|
|
},
|
|
"class": "local"
|
|
}
|