You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
gcgj-dify-1.7.0/api/core/model_runtime/model_providers
-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>
11 months ago
..
__base chore(*): Update style of thinking (#13319) 1 year ago
anthropic fix: handle document fetching from URL in Anthropic LLM model, solving base64 decoding error (#11858) 1 year ago
azure_ai_studio feat: add completion mode and context size options for LLM configuration (#13325) 1 year ago
azure_openai feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129) 1 year ago
baichuan fix: volcengine_maas and baichuan message error (#11625) 1 year ago
bedrock add bedrock deepseek-r1 (#18908) 11 months ago
chatglm chore: refurbish Python code by applying refurb linter rules (#8296) 2 years ago
cohere refactor: avoid to use extra space when finding model by name (#13043) 1 year ago
deepseek fix: correct linewrap think display in generic openai api (#13260) 1 year ago
fireworks feat: mypy for all type check (#10921) 1 year ago
fishaudio fix: fish audio wrong validate credentials interface (#11019) 1 year ago
gitee_ai fix: Update the API call address for the text_embedding model (#12342) 1 year ago
google fix: change gemini-2.0-flash to validate google api #17082 (#17115) 12 months ago
gpustack Support TTS and Speech2Text for Model Provider GPUStack (#12381) 1 year ago
groq feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229) 1 year ago
huggingface_hub chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702) 1 year ago
huggingface_tei fix: fix typo (#12034) 1 year ago
hunyuan feat:Add support for stop parameter in hunyuan model #12313 (#12315) 1 year ago
jina feat: mypy for all type check (#10921) 1 year ago
leptonai chore(api/core): apply ruff reformatting (#7624) 2 years ago
localai chore: format get_customizable_model_schema return value (#9335) 1 year ago
minimax feat:Support Minimax-Text-01 (#12763) 1 year ago
mistralai [Pixtral] Add new model ; add vision (#11231) 1 year ago
mixedbread refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 1 year ago
moonshot fix: DeepSeek API Error with response format active (text and json_object) (#12747) 1 year ago
nomic feat: mypy for all type check (#10921) 1 year ago
novita Fixed Novita AI color and added DeepSeek R1 model (#13074) 1 year ago
nvidia feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269) 1 year ago
nvidia_nim chore(api/core): apply ruff reformatting (#7624) 2 years ago
oci Upgrade oracle models (#13174) 1 year ago
ollama chore:improve thinking display for llm from xinference and ollama pro… (#13318) 1 year ago
openai fix: Removes redundant token calculations and updates dependencies 11 months ago
openai_api_compatible chore: refactor the OpenAICompatible and improve thinking display (#13299) 1 year ago
openllm feat: mypy for all type check (#10921) 1 year ago
openrouter feat(model): add deepseek-r1 for openrouter (#13312) 1 year ago
perfxcloud refactor: reduce duplciate code by inheritance (#13073) 1 year ago
replicate feat: mypy for all type check (#10921) 1 year ago
sagemaker [Fix] revert sagemaker llm to support model hub (#12378) 1 year ago
siliconflow fix: correct linewrap think display in generic openai api (#13260) 1 year ago
spark fix: SparkLite API Auth error (#12781) (#12790) 1 year ago
stepfun fix: #12143 support streaming mode content start with "data:" (#12171) 1 year ago
tencent chore: refurbish Python code by applying refurb linter rules (#8296) 2 years ago
togetherai feat: mypy for all type check (#10921) 1 year ago
tongyi add tongyi qwen2.5-14b/7b-instruct-1m model (#13089) 1 year ago
triton_inference_server chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702) 1 year ago
upstage feat: mypy for all type check (#10921) 1 year ago
vertex_ai fix: fix vertex gemini 2.0 flash 001 schema (#18405) 11 months ago
vessl_ai feat: mypy for all type check (#10921) 1 year ago
volcengine_maas feat: add deepseek models for volcengine provider (#13283) 1 year ago
voyage fix: int None will cause error for context size (#11055) 1 year ago
wenxin chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702) 1 year ago
x feat: add grok-2-1212 and grok-2-vision-1212 (#11672) 1 year ago
xinference chore:improve thinking display for llm from xinference and ollama pro… (#13318) 1 year ago
yi feat: mypy for all type check (#10921) 1 year ago
zhinao chore(api/core): apply ruff reformatting (#7624) 2 years ago
zhipuai feat: add glm-4-air-0111 (#12997) 1 year ago
__init__.py Model Runtime (#1858) 2 years ago
_position.yaml chore(model_runtime): Move deepseek ahead in the providers list. (#13197) 1 year ago
model_provider_factory.py feat: support pinning, including, and excluding for model providers and tools (#7419) 2 years ago