mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-08 08:28:02 +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>
94 lines
1.8 KiB
JSON
94 lines
1.8 KiB
JSON
{
|
|
"name": "TogetherAI",
|
|
"url": {
|
|
"default": "https://api.together.ai/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models",
|
|
"embedding": "embeddings",
|
|
"rerank": "rerank",
|
|
"asr": "audio/transcriptions",
|
|
"tts": "audio/speech"
|
|
},
|
|
"class": "together",
|
|
"models": [
|
|
{
|
|
"name": "openai/gpt-oss-20b",
|
|
"content_length": 131072,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
|
"content_length": 131072,
|
|
"max_output": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
|
|
"content_length": 262144,
|
|
"max_output": 65536,
|
|
"model_types": [
|
|
"chat"
|
|
],
|
|
"tools": {
|
|
"support": true
|
|
}
|
|
},
|
|
{
|
|
"name": "intfloat/multilingual-e5-large-instruct",
|
|
"max_tokens": 514,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 2048
|
|
},
|
|
{
|
|
"name": "BAAI/bge-large-en-v1.5",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 2048
|
|
},
|
|
{
|
|
"name": "BAAI/bge-base-en-v1.5",
|
|
"max_tokens": 512,
|
|
"model_types": [
|
|
"embedding"
|
|
],
|
|
"batch_size": 2048
|
|
},
|
|
{
|
|
"name": "mixedbread-ai/mxbai-rerank-large-v2",
|
|
"max_tokens": 16384,
|
|
"model_types": [
|
|
"rerank"
|
|
]
|
|
},
|
|
{
|
|
"name": "openai/whisper-large-v3",
|
|
"model_types": [
|
|
"asr"
|
|
]
|
|
},
|
|
{
|
|
"name": "canopylabs/orpheus-3b-0.1-ft",
|
|
"model_types": [
|
|
"tts"
|
|
]
|
|
}
|
|
]
|
|
}
|