Sākums Izpētīt Palīdzība
Pierakstīties
ignatz
/
dify-forked
1
0
Atdalīts 0
Faili Problēmas 0 Izmaiņu pieprasījumi 0 Vikivietne
Koks: a5d6082418
Atzari Tagi
dify-forked
/
api
/
core
/
model_runtime
/
model_providers
Warren Chen 631cbcd781 [fix] rename yaml files to fit windows (#11379) 1 gadu atpakaļ
..
__base c5f7d650b5 feat: Allow using file variables directly in the LLM node and support more file types. (#10679) 1 gadu atpakaļ
anthropic 02572e8cca fix: claude can not handle empty string (#11238) 1 gadu atpakaļ
azure_ai_studio 51db59622c chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425) 1 gadu atpakaļ
azure_openai 6f9ce6a199 fix: fix azure open-4o-08-06 when enable json schema cant process content = "" (#11204) 1 gadu atpakaļ
baichuan b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 gadu atpakaļ
bedrock 631cbcd781 [fix] rename yaml files to fit windows (#11379) 1 gadu atpakaļ
chatglm 40fb4d16ef chore: refurbish Python code by applying refurb linter rules (#8296) 1 gadu atpakaļ
cohere 0067b16d1e fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883) 1 gadu atpakaļ
deepseek aae29e72ae Fix Deepseek Function/Tool Calling (#11023) 1 gadu 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) 1 gadu atpakaļ
gitee_ai 40fc6f529e fix: gitee ai wrong default model, and better para (#11168) 1 gadu atpakaļ
google 594666eb61 fix: use Gemini response metadata for token counting (#11226) 1 gadu atpakaļ
gpustack 8aae235a71 fix: int None will cause error for context size (#11055) 1 gadu atpakaļ
groq b92504bebc Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479) 1 gadu 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) 1 gadu 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) 1 gadu 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 5b8f03cd9d add abab7-chat-preview model (#10654) 1 gadu atpakaļ
mistralai 5ddb601e43 add MixtralAI Model (#8517) 1 gadu 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) 1 gadu 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 8aae235a71 fix: int None will cause error for context size (#11055) 1 gadu atpakaļ
openai aa135a3780 Add TTS to OpenAI_API_Compatible (#11071) 1 gadu atpakaļ
openai_api_compatible 643a90c48d fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) 1 gadu atpakaļ
openllm 0067b16d1e fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883) 1 gadu atpakaļ
openrouter 4d6b45427c Support streaming output for OpenAI o1-preview and o1-mini (#10890) 1 gadu atpakaļ
perfxcloud 8aae235a71 fix: int None will cause error for context size (#11055) 1 gadu 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) 1 gadu atpakaļ
siliconflow a4fc057a1c ISSUE=11042: add tts model in siliconflow (#11043) 1 gadu 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) 1 gadu 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 08ac36812b feat: support LLM process document file (#10966) 1 gadu 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 8aae235a71 fix: int None will cause error for context size (#11055) 1 gadu atpakaļ
vessl_ai aa895cfa9b fix: [VESSL-AI] edit some words in vessl_ai.yaml (#10417) 1 gadu atpakaļ
volcengine_maas e79eac688a chore(lint): sort __all__ definitions (#11243) 1 gadu atpakaļ
voyage 8aae235a71 fix: int None will cause error for context size (#11055) 1 gadu atpakaļ
wenxin e39e776d03 fix: better wenxin rerank handler, close #11252 (#11283) 1 gadu atpakaļ
x 1065917872 Add grok-vision-beta to xAI + Update grok-beta Features (#11004) 1 gadu atpakaļ
xinference 03ba4bc760 fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012) 1 gadu 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 91e1ff5e30 chore: improve zhipu LLM (#11321) 1 gadu atpakaļ
__init__.py d069c668f8 Model Runtime (#1858) 2 gadi 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