conf/models/ollama.json

{
  "name": "Ollama",
  "rank": 978,
  "url_suffix": {
    "chat": "api/chat",
    "models": "api/tags",
    "embedding": "api/embed"
  },
  "class": "local"
}
Go: implement provider: Ollama (#14580) ### What problem does this PR solve? implement `Ollama` provider ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com> 2026-05-06 12:03:58 +08:00			`{`
Fix: provider name (#16733) 2026-07-09 10:19:10 +08:00			`"name": "Ollama",`
Fix Go: list providers order issue. (#16616) ### Summary As title. --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com> 2026-07-03 18:27:32 +08:00			`"rank": 978,`
Go: implement provider: Ollama (#14580) ### What problem does this PR solve? implement `Ollama` provider ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com> 2026-05-06 12:03:58 +08:00			`"url_suffix": {`
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213) ### 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 2026-05-25 18:55:03 +08:00			`"chat": "api/chat",`
fix: use /api/tags endpoint for Ollama model listing (#16000) (#16003) After upgrading to v0.26.0, the Ollama provider returns an empty model list because the Go rewrite uses `/api/ps` (only running models) instead of `/api/tags` (all installed models). This PR changes the endpoint to `/api/tags`, restoring the ability to list and add Ollama models. Closes #16000 2026-06-14 22:20:15 -04:00			`"models": "api/tags",`
fix(Go): rewrite chat, listmodels, embed for Ollama (#15213) ### 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 2026-05-25 18:55:03 +08:00			`"embedding": "api/embed"`
Go: implement provider: Ollama (#14580) ### What problem does this PR solve? implement `Ollama` provider ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Co-authored-by: Jin Hai <haijin.chn@gmail.com> 2026-05-06 12:03:58 +08:00			`},`
			`"class": "local"`
Fix: provider name (#16733) 2026-07-09 10:19:10 +08:00			`}`