mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-08 16:38:01 +08:00
2e2d12d262
## Summary Add a `batch_size` field to every embedding model entry in `conf/models/*.json`. The field represents the maximum number of text inputs that can be submitted to the embedding API in a single request. **75 embedding models across 30 config files** now carry a `batch_size`. Values were verified against each provider's official documentation (see the verification table at `Desktop/embedding_models_verified.md`). ## Distribution | batch_size | # models | Provider / Model | |---|---|---| | 1 | 2 | AWS Bedrock `amazon.titan-embed-text-v1/v2:0` — Bedrock `invoke` accepts a single input per call | | 10 | 3 | Aliyun `text-embedding-v3/v4`, Volcengine `doubao-embedding-vision-251215` | | 16 | 5 | BaiChuan `Baichuan-Text-Embedding`, Baidu Qianfan `embedding-v1`, Mistral `mistral-embed`, Replicate (x2) | | 32 | 10 | NVIDIA NIM (x3), SILICONFLOW (x2), PPIO (x3), GiteeAI `bge-m3`, HuaweiCloud `bge-m3` | | 50 | 4 | Tencent Hunyuan `kinfra` embeddings (x4) — `InputList.N` max 50 | | 96 | 8 | Cohere embed-v3/v4 (x5), Bedrock Cohere (x3) | | 100 | 3 | Google Gemini `text-embedding-004`, Upstage (x2) | | 512 | 5 | Zhipu GLM `embedding-2/3` (x2), Perplexity `pplx-embed` (x2), Astraflow `text-embedding-3-large` | | 1000 | 9 | Voyage AI (x9) — API reference max | | 1024 | 1 | DeepInfra `Qwen/Qwen3-Embedding-4B` | | 2048 | 15 | OpenAI (x3) + OpenAI-API-compatible proxies (CometAPI, n1n, Jiekou.AI, GreenPT, TogetherAI, NovitaAI) — OpenAI contract limit | | 16384 | 10 | Jina (x8), 302.AI, GiteeAI `jina-clip-v2` — no documented Jina batch limit, safe high cap | --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
91 lines
1.7 KiB
JSON
91 lines
1.7 KiB
JSON
{
|
|
"name": "Tongyi-Qianwen",
|
|
"rank": 983,
|
|
"url": {
|
|
"default": "https://dashscope.aliyuncs.com",
|
|
"singapore": "https://dashscope-intl.aliyuncs.com",
|
|
"us": "https://dashscope-us.aliyuncs.com"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "compatible-mode/v1/chat/completions",
|
|
"embedding": "compatible-mode/v1/embeddings",
|
|
"rerank": "compatible-api/v1/reranks",
|
|
"models": "compatible-mode/v1/models",
|
|
"tts": "compatible-mode/v1/audio/speech"
|
|
},
|
|
"models": [
|
|
{
|
|
"name": "qwen-flash",
|
|
"content_length": 1048576,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "text-embedding-v4",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 10
|
|
},
|
|
{
|
|
"name": "qwen3-vl-plus",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"vision",
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "qwen-tts-flash",
|
|
"model_types": [
|
|
"tts"
|
|
]
|
|
},
|
|
{
|
|
"name": "qwen-asr-flash",
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
},
|
|
{
|
|
"name": "fun-asr",
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
},
|
|
{
|
|
"name": "text-embedding-v3",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 10
|
|
},
|
|
{
|
|
"name": "qwen3-rerank",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
}
|
|
],
|
|
"features": {
|
|
"thinking": {
|
|
"default_value": true,
|
|
"supported_models": [
|
|
"qwen-flash"
|
|
]
|
|
}
|
|
}
|
|
}
|