-LAN- 559ab46ee1 fix: Removes redundant token calculations and updates dependencies ... Eliminates unnecessary pre-calculation of token limits and recalculation of max tokens across multiple app runners, simplifying the logic for prompt handling. Updates tiktoken library from version 0.8.0 to 0.9.0 for improved tokenization performance. Increases default token limit in TokenBufferMemory to accommodate larger prompt messages. These changes streamline the token management process and leverage the latest improvements in the tiktoken library. Fixes potential token overflow issues and prepares the system for handling larger inputs more efficiently. Relates to internal optimization tasks. Signed-off-by: -LAN- <laipz8200@outlook.com>		2025-04-28 15:39:12 +08:00
..
__base	chore(*): Update style of thinking (#13319)	2025-02-07 14:06:35 +08:00
anthropic	fix: handle document fetching from URL in Anthropic LLM model, solving base64 decoding error (#11858)	2024-12-20 18:23:42 +08:00
azure_ai_studio	feat: add completion mode and context size options for LLM configuration (#13325)	2025-02-07 15:08:53 +08:00
azure_openai	feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129)	2025-02-05 17:04:45 +08:00
baichuan	fix: volcengine_maas and baichuan message error (#11625)	2024-12-16 13:05:27 +08:00
bedrock	add bedrock deepseek-r1 (#18908)	2025-04-27 19:30:42 +08:00
chatglm	chore: refurbish Python code by applying refurb linter rules (#8296)	2024-09-12 15:50:49 +08:00
cohere	refactor: avoid to use extra space when finding model by name (#13043)	2025-01-30 15:08:29 +08:00
deepseek	fix: correct linewrap think display in generic openai api (#13260)	2025-02-06 10:53:08 +08:00
fireworks	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
fishaudio	fix: fish audio wrong validate credentials interface (#11019)	2024-11-23 23:39:41 +08:00
gitee_ai	fix: Update the API call address for the text_embedding model (#12342)	2025-01-03 19:19:17 +08:00
google	fix: change gemini-2.0-flash to validate google api #17082 (#17115)	2025-03-30 13:04:12 +08:00
gpustack	Support TTS and Speech2Text for Model Provider GPUStack (#12381)	2025-01-07 09:42:11 +08:00
groq	feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229)	2025-02-05 19:15:29 +08:00
huggingface_hub	chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)	2025-01-21 10:12:29 +08:00
huggingface_tei	fix: fix typo (#12034)	2024-12-24 15:23:27 +08:00
hunyuan	feat:Add support for stop parameter in hunyuan model #12313 (#12315)	2025-01-03 09:15:04 +08:00
jina	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
leptonai	chore(api/core): apply ruff reformatting (#7624)	2024-09-10 17:00:20 +08:00
localai	chore: format get_customizable_model_schema return value (#9335)	2024-10-21 19:05:44 +08:00
minimax	feat:Support Minimax-Text-01 (#12763)	2025-01-21 10:08:53 +08:00
mistralai	[Pixtral] Add new model ; add vision (#11231)	2024-12-11 10:14:16 +08:00
mixedbread	refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)	2024-10-17 19:12:42 +08:00
moonshot	fix: DeepSeek API Error with response format active (text and json_object) (#12747)	2025-01-20 22:04:18 +08:00
nomic	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
novita	Fixed Novita AI color and added DeepSeek R1 model (#13074)	2025-01-28 10:38:54 +08:00
nvidia	feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269)	2025-02-06 13:03:19 +08:00
nvidia_nim	chore(api/core): apply ruff reformatting (#7624)	2024-09-10 17:00:20 +08:00
oci	Upgrade oracle models (#13174)	2025-02-06 13:24:27 +08:00
ollama	chore:improve thinking display for llm from xinference and ollama pro… (#13318)	2025-02-07 14:29:29 +08:00
openai	fix: Removes redundant token calculations and updates dependencies	2025-04-28 15:39:12 +08:00
openai_api_compatible	chore: refactor the OpenAICompatible and improve thinking display (#13299)	2025-02-07 13:28:46 +08:00
openllm	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
openrouter	feat(model): add deepseek-r1 for openrouter (#13312)	2025-02-07 12:39:13 +08:00
perfxcloud	refactor: reduce duplciate code by inheritance (#13073)	2025-01-28 10:52:01 +08:00
replicate	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
sagemaker	[Fix] revert sagemaker llm to support model hub (#12378)	2025-01-06 18:01:45 +08:00
siliconflow	fix: correct linewrap think display in generic openai api (#13260)	2025-02-06 10:53:08 +08:00
spark	fix: SparkLite API Auth error (#12781) (#12790)	2025-01-20 22:21:21 +08:00
stepfun	fix: #12143 support streaming mode content start with "data:" (#12171)	2025-01-03 16:33:37 +08:00
tencent	chore: refurbish Python code by applying refurb linter rules (#8296)	2024-09-12 15:50:49 +08:00
togetherai	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
tongyi	add tongyi qwen2.5-14b/7b-instruct-1m model (#13089)	2025-01-29 11:58:01 +08:00
triton_inference_server	chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)	2025-01-21 10:12:29 +08:00
upstage	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
vertex_ai	fix: fix vertex gemini 2.0 flash 001 schema (#18405)	2025-04-19 22:04:13 +08:00
vessl_ai	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
volcengine_maas	feat: add deepseek models for volcengine provider (#13283)	2025-02-06 18:20:03 +08:00
voyage	fix: int None will cause error for context size (#11055)	2024-11-25 21:04:16 +08:00
wenxin	chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702)	2025-01-21 10:12:29 +08:00
x	feat: add grok-2-1212 and grok-2-vision-1212 (#11672)	2024-12-15 21:18:24 +08:00
xinference	chore:improve thinking display for llm from xinference and ollama pro… (#13318)	2025-02-07 14:29:29 +08:00
yi	feat: mypy for all type check (#10921)	2024-12-24 18:38:51 +08:00
zhinao	chore(api/core): apply ruff reformatting (#7624)	2024-09-10 17:00:20 +08:00
zhipuai	feat: add glm-4-air-0111 (#12997)	2025-01-24 10:04:46 +08:00
__init__.py	Model Runtime (#1858)	2024-01-02 23:42:00 +08:00
_position.yaml	chore(model_runtime): Move deepseek ahead in the providers list. (#13197)	2025-02-05 16:08:28 +08:00
model_provider_factory.py	feat: support pinning, including, and excluding for model providers and tools (#7419)	2024-08-21 11:16:43 +08:00