| .. | 
		
		
			
			
			
				
					| __base | c5f7d650b5
					feat: Allow using file variables directly in the LLM node and support more file types. (#10679) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| anthropic | 02572e8cca
					fix: claude can not handle empty string (#11238) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| azure_ai_studio | 51db59622c
					chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| azure_openai | 6f9ce6a199
					fix: fix azure open-4o-08-06 when enable json schema cant process content = "" (#11204) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| baichuan | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| bedrock | f54225568c
					fix(model_runtime): add vision to Amazon Nova Lite and Pro (#11398) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| chatglm | 40fb4d16ef
					chore: refurbish Python code by applying refurb linter rules (#8296) | 1 gadu atpakaļ | 
		
			
			
			
				
					| cohere | 5093337de1
					FEAT: cohere rerank 3.5 model added (#11289) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| deepseek | aae29e72ae
					Fix Deepseek Function/Tool Calling (#11023) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| fireworks | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| fishaudio | 448a19bf54
					fix: fish audio wrong validate credentials interface (#11019) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| gitee_ai | 40fc6f529e
					fix: gitee ai wrong default model, and better para (#11168) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| google | 1ce51e57ab
					feat: add gemini exp 1206 (#11444) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| gpustack | 8aae235a71
					fix: int None will cause error for context size (#11055) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| groq | 80c52e0ea4
					feat: Add llama-3.3 models for Groq (#11533) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| huggingface_hub | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| huggingface_tei | 096c0ad564
					feat: Add support for TEI API key authentication (#11006) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| hunyuan | 92a3898540
					fix: resolve the incorrect model name of hunyuan-standard-256k (#10052) | 1 gadu atpakaļ | 
		
			
			
			
				
					| jina | 8aae235a71
					fix: int None will cause error for context size (#11055) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| leptonai | 2cf1187b32
					chore(api/core): apply ruff reformatting (#7624) | 1 gadu atpakaļ | 
		
			
			
			
				
					| localai | 1e829ceaf3
					chore: format get_customizable_model_schema return value (#9335) | 1 gadu atpakaļ | 
		
			
			
			
				
					| minimax | 32f8439143
					fix: add the missing abab6.5t-chat model of Minimax (#11484) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| mistralai | 42d986b96d
					[Pixtral] Add new model ; add vision (#11231) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| mixedbread | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| moonshot | 643a90c48d
					fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| nomic | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| novita | 2cf1187b32
					chore(api/core): apply ruff reformatting (#7624) | 1 gadu atpakaļ | 
		
			
			
			
				
					| nvidia | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| nvidia_nim | 2cf1187b32
					chore(api/core): apply ruff reformatting (#7624) | 1 gadu atpakaļ | 
		
			
			
			
				
					| oci | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| ollama | 7e1184c071
					feat: support json_schema for ollama models (#11449) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| openai | aa135a3780
					Add TTS to OpenAI_API_Compatible (#11071) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| openai_api_compatible | 643a90c48d
					fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| openllm | 0067b16d1e
					fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| openrouter | 4d6b45427c
					Support streaming output for OpenAI o1-preview and o1-mini (#10890) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| perfxcloud | 8aae235a71
					fix: int None will cause error for context size (#11055) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| replicate | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| sagemaker | 51db59622c
					chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| siliconflow | ec00b25793
					feat: add siliconflow qwq and llama3.3 model (#11492) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| spark | d0e0111f88
					fix:Spark's large language model token calculation error #7911 (#8755) | 1 gadu atpakaļ | 
		
			
			
			
				
					| stepfun | 643a90c48d
					fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| tencent | 40fb4d16ef
					chore: refurbish Python code by applying refurb linter rules (#8296) | 1 gadu atpakaļ | 
		
			
			
			
				
					| togetherai | 2cf1187b32
					chore(api/core): apply ruff reformatting (#7624) | 1 gadu atpakaļ | 
		
			
			
			
				
					| tongyi | fbc4ca980c
					fix: Remove duplicate 'response_format' parameter from model YAML files (#11531) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| triton_inference_server | 1e829ceaf3
					chore: format get_customizable_model_schema return value (#9335) | 1 gadu atpakaļ | 
		
			
			
			
				
					| upstage | b90ad587c2
					refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) | 1 gadu atpakaļ | 
		
			
			
			
				
					| vertex_ai | 4d7cfd0de5
					Fix model provider of vertex ai (#11437) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| vessl_ai | aa895cfa9b
					fix: [VESSL-AI] edit some words in vessl_ai.yaml (#10417) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| volcengine_maas | e79eac688a
					chore(lint): sort __all__ definitions (#11243) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| voyage | 8aae235a71
					fix: int None will cause error for context size (#11055) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| wenxin | e39e776d03
					fix: better wenxin rerank handler, close #11252 (#11283) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| x | 1065917872
					Add grok-vision-beta to xAI + Update grok-beta Features (#11004) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| xinference | 03ba4bc760
					fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) | 11 mēneši atpakaļ | 
		
			
			
			
				
					| yi | e0846792d2
					feat: add yi custom llm intergration (#9482) | 1 gadu atpakaļ | 
		
			
			
			
				
					| zhinao | 2cf1187b32
					chore(api/core): apply ruff reformatting (#7624) | 1 gadu atpakaļ | 
		
			
			
			
				
					| zhipuai | 142b4fd699
					feat: add zhipu glm_4v_flash (#11440) | 10 mēneši atpakaļ | 
		
			
			
			
				
					| __init__.py | d069c668f8
					Model Runtime (#1858) | 1 gadu atpakaļ | 
		
			
			
			
				
					| _position.yaml | fb49413a41
					feat: add voyage ai as a new model provider (#8747) | 1 gadu atpakaļ | 
		
			
			
			
				
					| model_provider_factory.py | 4e7b6aec3a
					feat: support pinning, including, and excluding for model providers and tools (#7419) | 1 gadu atpakaļ |