mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-09 00:47:59 +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>
164 lines
3.0 KiB
JSON
164 lines
3.0 KiB
JSON
{
|
|
"name": "Cohere",
|
|
"rank": 990,
|
|
"url": {
|
|
"default": "https://api.cohere.com"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "v2/chat",
|
|
"models": "v1/models",
|
|
"embedding": "v2/embed",
|
|
"rerank": "v2/rerank",
|
|
"asr": "audio/transcriptions"
|
|
},
|
|
"class": "cohere",
|
|
"models": [
|
|
{
|
|
"name": "command-a-plus-05-2026",
|
|
"content_length": 131072,
|
|
"max_output": 65536,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-a-03-2025",
|
|
"content_length": 262144,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-r7b-12-2024",
|
|
"content_length": 131072,
|
|
"max_output": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-a-translate-08-2025",
|
|
"content_length": 8192,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-a-reasoning-08-2025",
|
|
"content_length": 262144,
|
|
"max_output": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-a-vision-07-2025",
|
|
"content_length": 131072,
|
|
"max_output": 8192,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-r-plus-08-2024",
|
|
"content_length": 131072,
|
|
"max_output": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "command-r-08-2024",
|
|
"content_length": 131072,
|
|
"max_output": 4096,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank-v4.0-pro",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank-v4.0-fast",
|
|
"max_tokens": 32768,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank-v3.5",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank-english-v3.0",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "rerank-multilingual-v3.0",
|
|
"max_tokens": 4096,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "embed-v4.0",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 96
|
|
},
|
|
{
|
|
"name": "embed-english-v3.0",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 96
|
|
},
|
|
{
|
|
"name": "embed-english-light-v3.0",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 96
|
|
},
|
|
{
|
|
"name": "embed-multilingual-v3.0",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 96
|
|
},
|
|
{
|
|
"name": "embed-multilingual-light-v3.0",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 96
|
|
},
|
|
{
|
|
"name": "cohere-transcribe-03-2026",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
}
|
|
]
|
|
}
|