7d4722b62c
- 实现QA数据 - 优化现在创建知识库的体验 - 优化文件处理与加载方法 - 整体的格式检查与优化 - 优化 Embedding model 的加载逻辑，修复并行问题 - 优化整体的颜色布局 - 移除未使用的接口（前后端） - 优化知识库的 chunk 逻辑 - 添加新的 Embedding模型支持 - 修复新建知识库后，Agent无法reload的问题
156 lines
3.9 KiB
YAML
156 lines
3.9 KiB
YAML
####################################################
|
||
#
|
||
# 不要直接修改这个里面的文件，可能会有被覆盖的风险，
|
||
# 建议 复制一份 在 models.private.yml 中修改，
|
||
# 会自动加载
|
||
#
|
||
#####################################################
|
||
|
||
MODEL_NAMES:
|
||
openai:
|
||
name: OpenAI
|
||
url: https://platform.openai.com/docs/models
|
||
base_url: https://api.openai.com/v1
|
||
default: gpt-3.5-turbo
|
||
env:
|
||
- OPENAI_API_KEY
|
||
models:
|
||
- gpt-4
|
||
- gpt-4o
|
||
- gpt-4o-mini
|
||
- gpt-3.5-turbo
|
||
|
||
deepseek:
|
||
name: DeepSeek
|
||
url: https://platform.deepseek.com/api-docs/zh-cn/pricing
|
||
base_url: https://api.deepseek.com/v1
|
||
default: deepseek-chat
|
||
env:
|
||
- DEEPSEEK_API_KEY
|
||
models:
|
||
- deepseek-chat
|
||
- deepseek-reasoner
|
||
|
||
zhipu:
|
||
name: 智谱AI (Zhipu)
|
||
url: https://open.bigmodel.cn/dev/api
|
||
base_url: https://open.bigmodel.cn/api/paas/v4/
|
||
default: glm-4-flash
|
||
env:
|
||
- ZHIPUAI_API_KEY
|
||
models:
|
||
- glm-4
|
||
- glm-4-plus
|
||
- glm-4-air
|
||
- glm-4-flash
|
||
- glm-z1-air
|
||
|
||
siliconflow:
|
||
name: SiliconFlow
|
||
url: https://cloud.siliconflow.cn/models
|
||
base_url: https://api.siliconflow.cn/v1
|
||
default: Qwen/Qwen3-8B
|
||
env:
|
||
- SILICONFLOW_API_KEY
|
||
models:
|
||
- Pro/deepseek-ai/DeepSeek-R1
|
||
- Pro/deepseek-ai/DeepSeek-V3
|
||
- Qwen/QwQ-32B
|
||
- Qwen/Qwen3-8B
|
||
|
||
together.ai:
|
||
name: Together.ai
|
||
url: https://api.together.ai/models
|
||
base_url: https://api.together.xyz/v1/
|
||
default: meta-llama/Llama-3.3-70B-Instruct-Turbo-Free
|
||
env:
|
||
- TOGETHER_API_KEY
|
||
models:
|
||
- meta-llama/Llama-3.3-70B-Instruct-Turbo
|
||
- meta-llama/Llama-3.3-70B-Instruct-Turbo-Free
|
||
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B-free
|
||
- Qwen/QwQ-32B
|
||
|
||
dashscope:
|
||
name: 阿里百炼 (DashScope)
|
||
url: https://bailian.console.aliyun.com/?switchAgent=10226727&productCode=p_efm#/model-market
|
||
base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
|
||
default: qwen3-235b-a22b
|
||
env:
|
||
- DASHSCOPE_API_KEY
|
||
models:
|
||
- qwen-max-latest
|
||
- qwen3-235b-a22b
|
||
- qwen3-32b
|
||
|
||
ark:
|
||
name: 豆包（Ark）
|
||
url: https://console.volcengine.com/ark/region:ark+cn-beijing/model
|
||
base_url: https://ark.cn-beijing.volces.com/api/v3
|
||
default: doubao-1-5-pro-32k-250115
|
||
env:
|
||
- ARK_API_KEY
|
||
models:
|
||
- doubao-1-5-pro-32k-250115
|
||
- doubao-1-5-lite-32k-250115
|
||
- deepseek-r1-250120
|
||
|
||
openrouter:
|
||
name: OpenRouter
|
||
url: https://openrouter.ai/models
|
||
base_url: https://openrouter.ai/api/v1
|
||
default: openai/gpt-4o
|
||
env:
|
||
- OPENROUTER_API_KEY
|
||
models:
|
||
- openai/gpt-4o
|
||
- openai/gpt-4o-mini
|
||
- google/gemini-2.5-pro-exp-03-25:free
|
||
- x-ai/grok-3-beta
|
||
- meta-llama/llama-4-maverick
|
||
- meta-llama/llama-4-maverick:free
|
||
- anthropic/claude-3.7-sonnet
|
||
- anthropic/claude-3.7-sonnet:thinking
|
||
|
||
|
||
EMBED_MODEL_INFO:
|
||
siliconflow/BAAI/bge-m3:
|
||
name: BAAI/bge-m3
|
||
dimension: 1024
|
||
base_url: https://api.siliconflow.cn/v1/embeddings
|
||
api_key: SILICONFLOW_API_KEY
|
||
|
||
siliconflow/Qwen/Qwen3-Embedding-0.6B:
|
||
name: Qwen/Qwen3-Embedding-0.6B
|
||
dimension: 1024
|
||
base_url: https://api.siliconflow.cn/v1/embeddings
|
||
api_key: SILICONFLOW_API_KEY
|
||
|
||
vllm/Qwen/Qwen3-Embedding-0.6B:
|
||
name: Qwen3-Embedding-0.6B
|
||
dimension: 1024
|
||
base_url: http://localhost:8081/v1/embeddings
|
||
api_key: no_api_key
|
||
|
||
ollama/nomic-embed-text:
|
||
name: nomic-embed-text
|
||
base_url: http://localhost:11434/api/embed
|
||
dimension: 768
|
||
|
||
ollama/bge-m3:
|
||
name: bge-m3
|
||
base_url: http://localhost:11434/api/embed
|
||
dimension: 1024
|
||
|
||
RERANKER_LIST:
|
||
|
||
siliconflow/BAAI/bge-reranker-v2-m3:
|
||
name: BAAI/bge-reranker-v2-m3
|
||
base_url: https://api.siliconflow.cn/v1/rerank
|
||
api_key: SILICONFLOW_API_KEY
|
||
|
||
vllm/Qwen/Qwen3-Reranker-0.6B:
|
||
name: Qwen/Qwen3-Reranker-0.6B
|
||
base_url: http://localhost:8081/v1/rerank
|
||
api_key: no_api_key
|