mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-08 00:18:12 +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>
108 lines
1.9 KiB
JSON
108 lines
1.9 KiB
JSON
{
|
|
"name": "GiteeAI",
|
|
"url": {
|
|
"default": "https://api.moark.ai/v1",
|
|
"china": "https://api.moark.com/v1",
|
|
"deprecated": "https://ai.gitee.com/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models",
|
|
"status": "",
|
|
"balance": "tokens/packages/balance",
|
|
"embedding": "embeddings",
|
|
"rerank": "rerank",
|
|
"ocr": "images/ocr",
|
|
"doc_parse": "async/documents/parse",
|
|
"tasks": "tasks",
|
|
"task": "task"
|
|
},
|
|
"models": [
|
|
{
|
|
"name": "qwen3-8b",
|
|
"content_length": 131072,
|
|
"max_output": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "qwen3-0.6b",
|
|
"content_length": 32768,
|
|
"max_output": 32768,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "glm-4.7-flash",
|
|
"content_length": 200000,
|
|
"max_output": 128000,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "BAAI/bge-reranker-v2-m3",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "BAAI/bge-m3",
|
|
"max_tokens": 8192,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 32
|
|
},
|
|
{
|
|
"name": "GOT-OCR2_0",
|
|
"model_types": [
|
|
"ocr"
|
|
]
|
|
},
|
|
{
|
|
"name": "DeepSeek-OCR-2",
|
|
"model_types": [
|
|
"ocr"
|
|
]
|
|
},
|
|
{
|
|
"name": "PaddleOCR-VL-1.5",
|
|
"model_types": [
|
|
"ocr"
|
|
]
|
|
},
|
|
{
|
|
"name": "jina-clip-v2",
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 16384
|
|
},
|
|
{
|
|
"name": "HunyuanOCR",
|
|
"model_types": [
|
|
"ocr"
|
|
]
|
|
},
|
|
{
|
|
"name": "MinerU2.5",
|
|
"model_types": [
|
|
"doc_parse"
|
|
]
|
|
}
|
|
]
|
|
}
|