From 405275935f9ce6dc6d9f80ea1659a0ff9beb7ccd Mon Sep 17 00:00:00 2001 From: Jin Hai Date: Thu, 6 Aug 2026 14:45:10 +0800 Subject: [PATCH] Go: fix unused check (#17922) Signed-off-by: Jin Hai --- conf/all_models.json | 430 +++++++++++++------------- conf/models/302ai.json | 2 +- conf/models/aliyun.json | 4 +- conf/models/astraflow.json | 2 +- conf/models/baichuan.json | 2 +- conf/models/baidu.json | 2 +- conf/models/bedrock.json | 10 +- conf/models/cohere.json | 10 +- conf/models/cometapi.json | 6 +- conf/models/deepinfra.json | 2 +- conf/models/gitee.json | 4 +- conf/models/google.json | 2 +- conf/models/greenpt.json | 2 +- conf/models/huaweicloud.json | 2 +- conf/models/hunyuan.json | 8 +- conf/models/jiekouai.json | 2 +- conf/models/jina.json | 16 +- conf/models/mistral.json | 2 +- conf/models/n1n.json | 6 +- conf/models/novita.json | 2 +- conf/models/nvidia.json | 6 +- conf/models/openai.json | 6 +- conf/models/perplexity.json | 4 +- conf/models/ppio.json | 6 +- conf/models/replicate.json | 4 +- conf/models/siliconflow.json | 4 +- conf/models/togetherai.json | 6 +- conf/models/upstage.json | 4 +- conf/models/volcengine.json | 2 +- conf/models/voyage.json | 18 +- conf/models/zhipu-ai.json | 4 +- internal/entity/models/anthropic.go | 5 +- internal/entity/models/google.go | 5 +- internal/entity/models/huaweicloud.go | 25 +- 34 files changed, 304 insertions(+), 311 deletions(-) diff --git a/conf/all_models.json b/conf/all_models.json index 6eac6bd09b..ea0c196f52 100644 --- a/conf/all_models.json +++ b/conf/all_models.json @@ -339,7 +339,7 @@ "dimensions": [], "content_length": 8192, "max_output": 8192, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "amazon/nova-2-Lite", @@ -361,7 +361,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "animate-anyone-detect-gen2", @@ -1114,7 +1114,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-large-en-v1.5", @@ -1124,14 +1124,14 @@ "max_dimension": 1024, "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-large-zh-v1.5", "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-en-icl", @@ -1144,7 +1144,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-m3", @@ -1158,7 +1158,7 @@ "dimensions": [], "content_length": 8192, "max_output": 8192, - "batch_size": 32 + "max_batch_size": 32 }, { "name": "BAAI/bge-m3-multi", @@ -1171,7 +1171,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "babbage-002", @@ -1543,7 +1543,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "Baichuan2-53B", @@ -2168,14 +2168,14 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "bge-large-zh-v1.5", "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "bigcode/starcoder2-15b-instruct-v0.1", @@ -3755,7 +3755,7 @@ 1024, 1536 ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/rerank-v4.0-fast", @@ -3800,7 +3800,7 @@ ], "max_dimension": 384, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/embed-english-v3.0", @@ -3812,7 +3812,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/embed-multilingual-light-v3.0", @@ -3824,7 +3824,7 @@ ], "max_dimension": 384, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/embed-multilingual-v3.0", @@ -3836,7 +3836,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/rerank-english-v3.0", @@ -3870,7 +3870,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/embed-english-v2.0", @@ -3882,7 +3882,7 @@ ], "max_dimension": 4096, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/embed-multilingual-v2.0", @@ -3894,7 +3894,7 @@ ], "max_dimension": 768, "dimensions": [], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere/cohere-transcribe-03-2026", @@ -5990,7 +5990,7 @@ ], "content_length": 4096, "max_output": 4096, - "batch_size": 10 + "max_batch_size": 10 }, { "name": "doubao-embedding-text-240515", @@ -6001,7 +6001,7 @@ "model_types": [ "embedding" ], - "batch_size": 10 + "max_batch_size": 10 }, { "name": "doubao-embedding-vision-241215", @@ -6016,7 +6016,7 @@ ], "content_length": 131072, "max_output": 131072, - "batch_size": 10 + "max_batch_size": 10 }, { "name": "doubao-lite-128k-240428", @@ -6605,7 +6605,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "emo-detect-v1", @@ -6995,7 +6995,7 @@ "model_types": [ "embedding" ], - "batch_size": 100 + "max_batch_size": 100 }, { "name": "gemini-embedding-2", @@ -7006,7 +7006,7 @@ "model_types": [ "embedding" ], - "batch_size": 100 + "max_batch_size": 100 }, { "name": "general_v2.0", @@ -8048,7 +8048,7 @@ 512, 768 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "google/embeddinggemma-300m-qat-q4_0-unquantized", @@ -8063,7 +8063,7 @@ 512, 768 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "google/embeddinggemma-300m-qat-q8_0-unquantized", @@ -8078,7 +8078,7 @@ 512, 768 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "google/functiongemma-270m-it", @@ -8099,7 +8099,7 @@ 1536, 3072 ], - "batch_size": 100 + "max_batch_size": 100 }, { "name": "google/gemini-embedding-2", @@ -8113,7 +8113,7 @@ 1536, 3072 ], - "batch_size": 100 + "max_batch_size": 100 }, { "name": "google/gemini-flash-latest", @@ -12099,7 +12099,7 @@ "dimensions": [], "content_length": 512, "max_output": 512, - "batch_size": 16 + "max_batch_size": 16 }, { "name": "ideogram", @@ -12290,7 +12290,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "intfloat/e5-large-v2", @@ -12303,7 +12303,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "intfloat/multilingual-e5-large", @@ -12316,7 +12316,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "intfloat/multilingual-e5-large-instruct", @@ -12330,7 +12330,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "inworld-ai/inworld-tts-1.5-max", @@ -12405,7 +12405,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-classification", @@ -12429,7 +12429,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-classification-GGUF", @@ -12453,7 +12453,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-classification-mlx", @@ -12477,7 +12477,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-clustering", @@ -12501,7 +12501,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-clustering-GGUF", @@ -12525,7 +12525,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-clustering-mlx", @@ -12549,7 +12549,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-mlx", @@ -12573,7 +12573,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-retrieval", @@ -12597,7 +12597,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF", @@ -12621,7 +12621,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-retrieval-mlx", @@ -12645,7 +12645,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-text-matching", @@ -12669,7 +12669,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-text-matching-GGUF", @@ -12693,7 +12693,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-nano-text-matching-mlx", @@ -12717,7 +12717,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small", @@ -12741,7 +12741,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-classification", @@ -12765,7 +12765,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-classification-GGUF", @@ -12789,7 +12789,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-classification-mlx", @@ -12813,7 +12813,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-clustering", @@ -12837,7 +12837,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-clustering-GGUF", @@ -12861,7 +12861,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-clustering-mlx", @@ -12885,7 +12885,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-mlx", @@ -12909,7 +12909,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-retrieval", @@ -12933,7 +12933,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-retrieval-GGUF", @@ -12957,7 +12957,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-retrieval-mlx", @@ -12981,7 +12981,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-text-matching", @@ -13005,7 +13005,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-text-matching-GGUF", @@ -13029,7 +13029,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-omni-small-text-matching-mlx", @@ -13053,7 +13053,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano", @@ -13075,7 +13075,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-classification", @@ -13097,7 +13097,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-classification-GGUF", @@ -13119,7 +13119,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-classification-mlx", @@ -13141,7 +13141,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-clustering", @@ -13163,7 +13163,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-clustering-GGUF", @@ -13185,7 +13185,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-clustering-mlx", @@ -13207,7 +13207,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-mlx", @@ -13229,7 +13229,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-retrieval", @@ -13251,7 +13251,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-retrieval-GGUF", @@ -13273,7 +13273,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-retrieval-mlx", @@ -13295,7 +13295,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-text-matching", @@ -13317,7 +13317,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-text-matching-GGUF", @@ -13339,7 +13339,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-nano-text-matching-mlx", @@ -13361,7 +13361,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small", @@ -13383,7 +13383,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-classification", @@ -13405,7 +13405,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-classification-GGUF", @@ -13427,7 +13427,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-classification-mlx", @@ -13449,7 +13449,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-clustering", @@ -13471,7 +13471,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-clustering-GGUF", @@ -13493,7 +13493,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-clustering-mlx", @@ -13515,7 +13515,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-mlx", @@ -13537,7 +13537,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-retrieval", @@ -13559,7 +13559,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-retrieval-GGUF", @@ -13581,7 +13581,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-retrieval-mlx", @@ -13603,7 +13603,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-text-matching", @@ -13625,7 +13625,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-text-matching-GGUF", @@ -13647,7 +13647,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v5-text-small-text-matching-mlx", @@ -13669,7 +13669,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4", @@ -13690,7 +13690,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-mlx-8bit", @@ -13711,7 +13711,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-text-code-GGUF", @@ -13731,7 +13731,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-text-matching-GGUF", @@ -13751,7 +13751,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-text-retrieval-GGUF", @@ -13771,7 +13771,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-vllm-code", @@ -13792,7 +13792,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-vllm-retrieval", @@ -13813,7 +13813,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v4-vllm-text-matching", @@ -13834,7 +13834,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v3", @@ -13856,7 +13856,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v3-hf", @@ -13878,7 +13878,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v3-small-ci", @@ -13900,7 +13900,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-reranker-v3", @@ -13973,7 +13973,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-colbert-v2", @@ -13989,7 +13989,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-colbert-v2-64", @@ -14005,7 +14005,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-base-code", @@ -14021,7 +14021,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-base-de", @@ -14037,7 +14037,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-base-en", @@ -14053,7 +14053,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-base-es", @@ -14069,7 +14069,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-base-zh", @@ -14085,7 +14085,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embeddings-v2-small-en", @@ -14101,7 +14101,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-reranker-v2-base-multilingual", @@ -14144,7 +14144,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-colbert-v1-en", @@ -14160,7 +14160,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embedding-b-en-v1", @@ -14176,7 +14176,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embedding-l-en-v1", @@ -14192,7 +14192,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embedding-s-en-v1", @@ -14208,7 +14208,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-embedding-t-en-v1", @@ -14224,7 +14224,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-reranker-v1-tiny-en", @@ -14346,7 +14346,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-code-embeddings-0.5b-GGUF", @@ -14365,7 +14365,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-code-embeddings-0.5b-mlx", @@ -14384,7 +14384,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-code-embeddings-1.5b", @@ -14403,7 +14403,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-code-embeddings-1.5b-GGUF", @@ -14422,7 +14422,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-code-embeddings-1.5b-mlx", @@ -14441,7 +14441,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jinaai/jina-reranker-m0", @@ -17869,7 +17869,7 @@ ], "content_length": 0, "max_output": 0, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "minimaxai/VTP-Large-f16d64", @@ -17886,7 +17886,7 @@ ], "content_length": 0, "max_output": 0, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "minimaxai/VTP-Small-f16d64", @@ -17903,7 +17903,7 @@ ], "content_length": 0, "max_output": 0, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "minimaxi-image-01", @@ -18036,7 +18036,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "mistral/mistral-large-latest", @@ -19159,7 +19159,7 @@ "model_types": [ "embedding" ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "netease-youdao/bce-reranker-base_v1", @@ -19971,7 +19971,7 @@ ], "max_dimension": 3072, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/llama-nemotron-embed-1b-v2", @@ -19989,7 +19989,7 @@ 1024, 2048 ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/llama-nemotron-embed-vl-1b-v2", @@ -20004,7 +20004,7 @@ "dimensions": [], "content_length": 10240, "max_output": 10240, - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/llama-nemotron-embed-vl-1b-v2-fp8", @@ -20017,7 +20017,7 @@ ], "max_dimension": 2048, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/llama-nemotron-rerank-1b-v2", @@ -20050,7 +20050,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nemotron-colembed-vl-8b-v2", @@ -20063,7 +20063,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nv-genmol-89m-v2", @@ -20367,7 +20367,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/llama-nemoretriever-colembed-3b-v1", @@ -20379,7 +20379,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/multitalker-parakeet-streaming-0.6b-v1", @@ -20491,7 +20491,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nv-genmol-89m-v1", @@ -20785,7 +20785,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv2-H", @@ -20798,7 +20798,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv2-L", @@ -20811,7 +20811,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv3-B", @@ -20824,7 +20824,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv3-g", @@ -20837,7 +20837,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv3-H", @@ -20850,7 +20850,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv3-L", @@ -20863,7 +20863,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv4-H", @@ -20876,7 +20876,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/C-RADIOv4-SO400M", @@ -20889,7 +20889,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/canary-1b", @@ -20956,7 +20956,7 @@ ], "max_dimension": 256, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/Cosmos-Embed1-336p", @@ -20969,7 +20969,7 @@ ], "max_dimension": 768, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/Cosmos-Embed1-448p", @@ -20982,7 +20982,7 @@ ], "max_dimension": 768, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/Cosmos-Embed1-448p-anomaly-detection", @@ -20995,7 +20995,7 @@ ], "max_dimension": 768, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/Cosmos-H-Surgical", @@ -21737,7 +21737,7 @@ ], "max_dimension": 3072, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/LocateAnything-3B", @@ -24041,7 +24041,7 @@ "dimensions": [ 512 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "openai/clip-vit-base-patch32", @@ -24057,7 +24057,7 @@ "dimensions": [ 512 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "openai/clip-vit-large-patch14", @@ -24072,7 +24072,7 @@ "dimensions": [ 768 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "openai/clip-vit-large-patch14-336", @@ -24088,7 +24088,7 @@ "dimensions": [ 768 ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "openai/consistency-decoder", @@ -24721,7 +24721,7 @@ ], "max_dimension": 3072, "dimensions": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "openai/text-embedding-3-small", @@ -24731,7 +24731,7 @@ ], "max_dimension": 1536, "dimensions": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "openai/text-embedding-ada-002", @@ -24741,7 +24741,7 @@ ], "max_dimension": 1536, "dimensions": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "openai/tts", @@ -26126,7 +26126,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "Qwen/Qwen3-Embedding-4B-batch", @@ -26139,7 +26139,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "Qwen/Qwen3-Embedding-8B-batch", @@ -26152,7 +26152,7 @@ ], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "Qwen/Qwen3-TTS", @@ -28751,7 +28751,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 32 + "max_batch_size": 32 }, { "name": "qwen/qwen3-embedding-0.6b-gguf", @@ -28765,7 +28765,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-embedding-4b", @@ -28779,7 +28779,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 1024 + "max_batch_size": 1024 }, { "name": "qwen/qwen3-embedding-4b-gguf", @@ -28793,7 +28793,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-embedding-8b", @@ -28807,7 +28807,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 32 + "max_batch_size": 32 }, { "name": "qwen/qwen3-embedding-8b-gguf", @@ -28821,7 +28821,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-forcedaligner-0.6b", @@ -29834,7 +29834,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-vl-embedding-2b", @@ -29848,7 +29848,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-vl-embedding-8b", @@ -29862,7 +29862,7 @@ "dimensions": [], "content_length": 32768, "max_output": 32768, - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "qwen/qwen3-vl-flash", @@ -34236,7 +34236,7 @@ "dimensions": [], "content_length": 384, "max_output": 384, - "batch_size": 16 + "max_batch_size": 16 }, { "name": "rerank-2.5", @@ -34821,7 +34821,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/all-MiniLM-L6-v2", @@ -34834,7 +34834,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/all-mpnet-base-v2", @@ -34847,7 +34847,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/paraphrase-MiniLM-L6-v2", @@ -34860,7 +34860,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/clip-ViT-B-32-multilingual-v1", @@ -34873,7 +34873,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/multi-qa-mpnet-base-dot-v1", @@ -34886,7 +34886,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sentence-transformers/clip-ViT-B-32", @@ -34899,7 +34899,7 @@ ], "content_length": 77, "max_output": 77, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "sesame/csm-1b", @@ -34961,7 +34961,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "slides_glm_agent", @@ -37580,7 +37580,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "tencent/MimicMotion", @@ -37600,7 +37600,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "tencent/Penguin-VL-2B", @@ -37866,7 +37866,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "tencent/Youtu-HiChunk", @@ -37879,7 +37879,7 @@ ], "max_dimension": null, "dimensions": [], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "tencent/Youtu-LLM-2B", @@ -37959,7 +37959,7 @@ "chat" ], "alias": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-3-small", @@ -37968,7 +37968,7 @@ "chat" ], "alias": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-ada-002", @@ -37977,7 +37977,7 @@ "chat" ], "alias": [], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-moderation-latest", @@ -38032,7 +38032,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "thenlper/gte-large", @@ -38045,7 +38045,7 @@ ], "content_length": 512, "max_output": 512, - "batch_size": 1 + "max_batch_size": 1 }, { "name": "THUDM/GLM-4.1V-9B-Thinking", @@ -38447,7 +38447,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-02", @@ -38459,7 +38459,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-2", @@ -38471,7 +38471,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-3", @@ -38483,7 +38483,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-3-large", @@ -38498,7 +38498,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-3-lite", @@ -38510,7 +38510,7 @@ ], "max_dimension": 512, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-3.5", @@ -38525,7 +38525,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-3.5-lite", @@ -38540,7 +38540,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-4", @@ -38557,7 +38557,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-4-large", @@ -38574,7 +38574,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-4-lite", @@ -38591,7 +38591,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-4-nano", @@ -38608,7 +38608,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-code-2", @@ -38618,7 +38618,7 @@ ], "max_dimension": 1536, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-code-3", @@ -38633,7 +38633,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-finance-2", @@ -38643,7 +38643,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-large-2", @@ -38655,7 +38655,7 @@ ], "max_dimension": 1536, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-large-2-instruct", @@ -38667,7 +38667,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-law-2", @@ -38677,7 +38677,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-lite-01", @@ -38689,7 +38689,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-lite-01-instruct", @@ -38701,7 +38701,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-lite-02-instruct", @@ -38713,7 +38713,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-multilingual-2", @@ -38725,7 +38725,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-multimodal-3", @@ -38740,7 +38740,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage/voyage-multimodal-3.5", @@ -38760,7 +38760,7 @@ 1024, 2048 ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-3-large", @@ -40763,7 +40763,7 @@ "dimensions": [], "content_length": 8192, "max_output": 8192, - "batch_size": 512 + "max_batch_size": 512 }, { "name": "zai-org/embedding-3", @@ -40782,7 +40782,7 @@ ], "content_length": 8192, "max_output": 8192, - "batch_size": 512 + "max_batch_size": 512 }, { "name": "zai-org/GLM-ASR-Nano-2512", @@ -41423,7 +41423,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 }, { "name": "Zyphra/Zonos-v0.1-hybrid", diff --git a/conf/models/302ai.json b/conf/models/302ai.json index d1e11c465f..fe85816685 100644 --- a/conf/models/302ai.json +++ b/conf/models/302ai.json @@ -294,7 +294,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-reranker-v2-base-multilingual", diff --git a/conf/models/aliyun.json b/conf/models/aliyun.json index 01c2e92349..d2a39c272f 100644 --- a/conf/models/aliyun.json +++ b/conf/models/aliyun.json @@ -31,7 +31,7 @@ "model_types": [ "embedding" ], - "batch_size": 10 + "max_batch_size": 10 }, { "name": "qwen3-vl-plus", @@ -69,7 +69,7 @@ "model_types": [ "embedding" ], - "batch_size": 10 + "max_batch_size": 10 }, { "name": "qwen3-rerank", diff --git a/conf/models/astraflow.json b/conf/models/astraflow.json index 97f246edfb..d065719dc3 100644 --- a/conf/models/astraflow.json +++ b/conf/models/astraflow.json @@ -19,7 +19,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 }, { "name": "bge-reranker-v2-m3", diff --git a/conf/models/baichuan.json b/conf/models/baichuan.json index c69be2ba1b..d1cf46eb92 100644 --- a/conf/models/baichuan.json +++ b/conf/models/baichuan.json @@ -125,7 +125,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 } ] } diff --git a/conf/models/baidu.json b/conf/models/baidu.json index e86119b9b1..edb8a99bd0 100644 --- a/conf/models/baidu.json +++ b/conf/models/baidu.json @@ -89,7 +89,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "qwen3-reranker-4b", diff --git a/conf/models/bedrock.json b/conf/models/bedrock.json index 954e92f258..6103f680ef 100644 --- a/conf/models/bedrock.json +++ b/conf/models/bedrock.json @@ -133,7 +133,7 @@ "model_types": [ "embedding" ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "amazon.titan-embed-text-v1", @@ -141,7 +141,7 @@ "model_types": [ "embedding" ], - "batch_size": 1 + "max_batch_size": 1 }, { "name": "cohere.embed-english-v3", @@ -149,7 +149,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere.embed-multilingual-v3", @@ -157,7 +157,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere.embed-v4:0", @@ -165,7 +165,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 } ] } diff --git a/conf/models/cohere.json b/conf/models/cohere.json index cd943f3cb6..3c2a212e2b 100644 --- a/conf/models/cohere.json +++ b/conf/models/cohere.json @@ -118,7 +118,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "embed-english-v3.0", @@ -126,7 +126,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "embed-english-light-v3.0", @@ -134,7 +134,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "embed-multilingual-v3.0", @@ -142,7 +142,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "embed-multilingual-light-v3.0", @@ -150,7 +150,7 @@ "model_types": [ "embedding" ], - "batch_size": 96 + "max_batch_size": 96 }, { "name": "cohere-transcribe-03-2026", diff --git a/conf/models/cometapi.json b/conf/models/cometapi.json index e316de475f..309fe3543c 100644 --- a/conf/models/cometapi.json +++ b/conf/models/cometapi.json @@ -125,7 +125,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-3-large", @@ -133,7 +133,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-ada-002", @@ -141,7 +141,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "whisper-1", diff --git a/conf/models/deepinfra.json b/conf/models/deepinfra.json index aa4387a0d7..d40a1367f7 100644 --- a/conf/models/deepinfra.json +++ b/conf/models/deepinfra.json @@ -35,7 +35,7 @@ "model_types": [ "embedding" ], - "batch_size": 1024 + "max_batch_size": 1024 }, { "name": "hexgrad/Kokoro-82M", diff --git a/conf/models/gitee.json b/conf/models/gitee.json index 035be6ce1d..d90646b5b8 100644 --- a/conf/models/gitee.json +++ b/conf/models/gitee.json @@ -64,7 +64,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "GOT-OCR2_0", @@ -89,7 +89,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "HunyuanOCR", diff --git a/conf/models/google.json b/conf/models/google.json index f3d14de163..322af0cba6 100644 --- a/conf/models/google.json +++ b/conf/models/google.json @@ -30,7 +30,7 @@ "model_types": [ "embedding" ], - "batch_size": 100 + "max_batch_size": 100 } ], "features": { diff --git a/conf/models/greenpt.json b/conf/models/greenpt.json index 9808b4bc57..f9ecbdefcf 100644 --- a/conf/models/greenpt.json +++ b/conf/models/greenpt.json @@ -44,7 +44,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "green-rerank", diff --git a/conf/models/huaweicloud.json b/conf/models/huaweicloud.json index 310a85f6f2..6b1f6a7050 100755 --- a/conf/models/huaweicloud.json +++ b/conf/models/huaweicloud.json @@ -219,7 +219,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "bge-reranker-v2-m3", diff --git a/conf/models/hunyuan.json b/conf/models/hunyuan.json index 2a2bcfe186..f9ae27c870 100644 --- a/conf/models/hunyuan.json +++ b/conf/models/hunyuan.json @@ -365,7 +365,7 @@ "model_types": [ "embedding" ], - "batch_size": 50 + "max_batch_size": 50 }, { "name": "kinfra-text-embedding-4b", @@ -373,7 +373,7 @@ "model_types": [ "embedding" ], - "batch_size": 50 + "max_batch_size": 50 }, { "name": "kinfra-vl-embedding-2b", @@ -381,7 +381,7 @@ "model_types": [ "embedding" ], - "batch_size": 50 + "max_batch_size": 50 }, { "name": "kinfra-vl-embedding-8b", @@ -389,7 +389,7 @@ "model_types": [ "embedding" ], - "batch_size": 50 + "max_batch_size": 50 } ] } diff --git a/conf/models/jiekouai.json b/conf/models/jiekouai.json index a4c2320eb4..9d471c434c 100644 --- a/conf/models/jiekouai.json +++ b/conf/models/jiekouai.json @@ -129,7 +129,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 } ] } diff --git a/conf/models/jina.json b/conf/models/jina.json index 28f2991ebb..81672bd884 100644 --- a/conf/models/jina.json +++ b/conf/models/jina.json @@ -57,7 +57,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v4", @@ -65,7 +65,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v5-text-small", @@ -73,7 +73,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v5-text-nano", @@ -81,7 +81,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v5-omni-small", @@ -89,7 +89,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v5-omni-nano", @@ -97,7 +97,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-clip-v2", @@ -105,7 +105,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 }, { "name": "jina-embeddings-v2-base-en", @@ -113,7 +113,7 @@ "model_types": [ "embedding" ], - "batch_size": 16384 + "max_batch_size": 16384 } ] } diff --git a/conf/models/mistral.json b/conf/models/mistral.json index 616b62db54..74241253bf 100644 --- a/conf/models/mistral.json +++ b/conf/models/mistral.json @@ -175,7 +175,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "mistral-ocr-2512", diff --git a/conf/models/n1n.json b/conf/models/n1n.json index 8a34da2a28..6ca465e8f2 100644 --- a/conf/models/n1n.json +++ b/conf/models/n1n.json @@ -120,7 +120,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-3-large", @@ -128,7 +128,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-ada-002", @@ -136,7 +136,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-reranker-v2-m3", diff --git a/conf/models/novita.json b/conf/models/novita.json index d2a5fa7e18..469e0493da 100644 --- a/conf/models/novita.json +++ b/conf/models/novita.json @@ -95,7 +95,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "baai/bge-reranker-v2-m3", diff --git a/conf/models/nvidia.json b/conf/models/nvidia.json index 05c7fb39b4..a0c87b9736 100644 --- a/conf/models/nvidia.json +++ b/conf/models/nvidia.json @@ -235,7 +235,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nemotron-3-nano-30b-a3b", @@ -317,7 +317,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nv-embedcode-7b-v1", @@ -325,7 +325,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "nvidia/nvidia-nemotron-nano-9b-v2", diff --git a/conf/models/openai.json b/conf/models/openai.json index 0c15f86ab8..0a78318f0c 100644 --- a/conf/models/openai.json +++ b/conf/models/openai.json @@ -256,7 +256,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-3-small", @@ -264,7 +264,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "text-embedding-3-large", @@ -272,7 +272,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "whisper-1", diff --git a/conf/models/perplexity.json b/conf/models/perplexity.json index 961976ec19..a8b979d643 100644 --- a/conf/models/perplexity.json +++ b/conf/models/perplexity.json @@ -52,7 +52,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 }, { "name": "pplx-embed-v1-4b", @@ -60,7 +60,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 } ] } diff --git a/conf/models/ppio.json b/conf/models/ppio.json index 6ce4441328..608f0c3483 100644 --- a/conf/models/ppio.json +++ b/conf/models/ppio.json @@ -248,21 +248,21 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "baai/bge-m3", "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "qwen/qwen3-embedding-0.6b", "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "baai/bge-reranker-v2-m3", diff --git a/conf/models/replicate.json b/conf/models/replicate.json index 103eb9b2e6..407d1ef6fb 100644 --- a/conf/models/replicate.json +++ b/conf/models/replicate.json @@ -48,7 +48,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 }, { "name": "ibm-granite/granite-embedding-278m-multilingual:1f76d42a05f120e12272746d5a2d86b525c13420773f795a4cbef9117d8685f1", @@ -56,7 +56,7 @@ "model_types": [ "embedding" ], - "batch_size": 16 + "max_batch_size": 16 } ] } diff --git a/conf/models/siliconflow.json b/conf/models/siliconflow.json index 1af3894b72..707c82efcf 100644 --- a/conf/models/siliconflow.json +++ b/conf/models/siliconflow.json @@ -121,7 +121,7 @@ "model_types": [ "embedding" ], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "BAAI/bge-m3", @@ -131,7 +131,7 @@ ], "max_dimension": 1024, "dimensions": [], - "batch_size": 32 + "max_batch_size": 32 }, { "name": "fnlp/MOSS-TTSD-v0.5", diff --git a/conf/models/togetherai.json b/conf/models/togetherai.json index e42c4945e5..1c6eb98d02 100644 --- a/conf/models/togetherai.json +++ b/conf/models/togetherai.json @@ -52,7 +52,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-large-en-v1.5", @@ -60,7 +60,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "BAAI/bge-base-en-v1.5", @@ -68,7 +68,7 @@ "model_types": [ "embedding" ], - "batch_size": 2048 + "max_batch_size": 2048 }, { "name": "mixedbread-ai/mxbai-rerank-large-v2", diff --git a/conf/models/upstage.json b/conf/models/upstage.json index 2162499780..92c9b95e86 100644 --- a/conf/models/upstage.json +++ b/conf/models/upstage.json @@ -60,7 +60,7 @@ "model_types": [ "embedding" ], - "batch_size": 100 + "max_batch_size": 100 }, { "name": "solar-embedding-1-large-passage", @@ -68,7 +68,7 @@ "model_types": [ "embedding" ], - "batch_size": 100 + "max_batch_size": 100 } ] } diff --git a/conf/models/volcengine.json b/conf/models/volcengine.json index 49743b464c..f443a8dd52 100644 --- a/conf/models/volcengine.json +++ b/conf/models/volcengine.json @@ -33,7 +33,7 @@ "model_types": [ "embedding" ], - "batch_size": 10 + "max_batch_size": 10 } ] } diff --git a/conf/models/voyage.json b/conf/models/voyage.json index fd4b29b1a3..2f34775a98 100644 --- a/conf/models/voyage.json +++ b/conf/models/voyage.json @@ -15,7 +15,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-4", @@ -23,7 +23,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-4-lite", @@ -31,7 +31,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-3.5", @@ -39,7 +39,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-3.5-lite", @@ -47,7 +47,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-3-large", @@ -55,7 +55,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-code-3", @@ -63,7 +63,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-law-2", @@ -71,7 +71,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "voyage-finance-2", @@ -79,7 +79,7 @@ "model_types": [ "embedding" ], - "batch_size": 1000 + "max_batch_size": 1000 }, { "name": "rerank-2.5", diff --git a/conf/models/zhipu-ai.json b/conf/models/zhipu-ai.json index 4f92c6ec4e..bc62b1f0c7 100644 --- a/conf/models/zhipu-ai.json +++ b/conf/models/zhipu-ai.json @@ -357,7 +357,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 }, { "name": "embedding-3", @@ -365,7 +365,7 @@ "model_types": [ "embedding" ], - "batch_size": 512 + "max_batch_size": 512 }, { "name": "glm-asr-2512", diff --git a/internal/entity/models/anthropic.go b/internal/entity/models/anthropic.go index 18832053e2..251d6ba624 100644 --- a/internal/entity/models/anthropic.go +++ b/internal/entity/models/anthropic.go @@ -81,9 +81,8 @@ func (a *AnthropicModel) ChatWithMessages(ctx context.Context, modelName string, baseURLRegion := a.region(apiConfig) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := a.baseModel.GetBaseURL(baseURLConfig) if err != nil { return nil, err diff --git a/internal/entity/models/google.go b/internal/entity/models/google.go index fb7d0230cb..958addcebc 100644 --- a/internal/entity/models/google.go +++ b/internal/entity/models/google.go @@ -172,9 +172,8 @@ func (g *GoogleModel) baseURL(apiConfig *APIConfig) string { baseURL, err := g.baseModel.GetBaseURL(apiConfig) if err != nil { defaultConfig := &APIConfig{} - if apiConfig != nil { - defaultConfig.BaseURL = apiConfig.BaseURL - } + defaultConfig.BaseURL = apiConfig.BaseURL + baseURL, err = g.baseModel.GetBaseURL(defaultConfig) if err != nil { return "" diff --git a/internal/entity/models/huaweicloud.go b/internal/entity/models/huaweicloud.go index d36514e4c6..350dc673df 100644 --- a/internal/entity/models/huaweicloud.go +++ b/internal/entity/models/huaweicloud.go @@ -173,9 +173,8 @@ func (h *HuaweiCloudModel) ChatWithMessages(ctx context.Context, modelName strin baseURLRegion := huaweiCloudRegionForModel(apiConfig, modelName) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := h.baseModel.GetBaseURL(baseURLConfig) if err != nil { return nil, err @@ -213,9 +212,8 @@ func (h *HuaweiCloudModel) ChatStreamlyWithSender(ctx context.Context, modelName baseURLRegion := huaweiCloudRegionForModel(apiConfig, modelName) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := h.baseModel.GetBaseURL(baseURLConfig) if err != nil { return err @@ -276,9 +274,8 @@ func (h *HuaweiCloudModel) Embed(ctx context.Context, modelName *string, texts [ baseURLRegion := huaweiCloudRegion(apiConfig) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := h.baseModel.GetBaseURL(baseURLConfig) if err != nil { return nil, err @@ -381,9 +378,8 @@ func (h *HuaweiCloudModel) Rerank(ctx context.Context, modelName *string, query baseURLRegion := huaweiCloudRegion(apiConfig) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := h.baseModel.GetBaseURL(baseURLConfig) if err != nil { return nil, err @@ -488,9 +484,8 @@ func (h *HuaweiCloudModel) ListModels(ctx context.Context, apiConfig *APIConfig) baseURLRegion := huaweiCloudRegion(apiConfig) baseURLConfig := &APIConfig{Region: &baseURLRegion} - if apiConfig != nil { - baseURLConfig.BaseURL = apiConfig.BaseURL - } + baseURLConfig.BaseURL = apiConfig.BaseURL + baseURL, err := h.baseModel.GetBaseURL(baseURLConfig) if err != nil { return nil, err