mkaaad 1b02abd487 Honor explicit model URL overrides for NVIDIA endpoints (#18152) ...

Some NVIDIA hosted models (e.g. meta/llama-3.2-11b-vision-instruct )
expose a full
endpoint URL per model that does not follow the normal base_url +
url_suffix
assembly. Previously the Go driver always called {base}/chat/completions
, so chat
requests for these vision models hit the wrong endpoint and failed.

This PR adds an optional per-model url field in conf/models/nvidia.json
. When
present, every NVIDIA driver request (chat, streaming chat, embedding,
rerank, model
listing) uses it directly; otherwise the standard assembly is unchanged.

2026-08-12 14:17:13 +08:00

..

302ai.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

aliyun.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

anthropic.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

astraflow.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

avian.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

azure-openai.json

feat(go-models): add Azure OpenAI model driver (#15022)

2026-05-21 11:52:56 +08:00

baichuan.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

baidu.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

bedrock.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

cohere.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

cometapi.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

deepinfra.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

deepseek.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

fishaudio.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

funasr.json

fix: Go backend builtin chunk method list not showing (#17180)

2026-07-22 19:14:51 +08:00

futurmix.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

gitee.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

google.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

gpustack.json

Go: implement Embed in GPUStack driver (#15182)

2026-06-01 11:22:43 +08:00

greenpt.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

groq.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

huaweicloud.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

huggingface.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

hunyuan.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

jiekouai.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

jina.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

lmstudio.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

localai.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

longcat.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

mineru_local.json

Go: implement embed for Tencent Hunyuan (#15207)

2026-05-25 16:04:17 +08:00

mineru.json

fix(go-models): route hosted OCR providers through drivers (#15233)

2026-05-26 20:40:40 +08:00

minimax.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

mistral.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

modelscope.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

moonshot.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

mws.json

Integrate MWS model with API support and enhance chat functionality (#17959)

2026-08-11 19:12:42 +08:00

n1n.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

novita.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

nvidia.json

Honor explicit model URL overrides for NVIDIA endpoints (#18152)

2026-08-12 14:17:13 +08:00

ollama.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

openai-api-compatible.json

Feat: OpenAI-API-Compatible (#17276)

2026-07-23 13:39:57 +08:00

openai.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

openrouter.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

orcarouter.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

paddleocr_local.json

Go: implement embed for Tencent Hunyuan (#15207)

2026-05-25 16:04:17 +08:00

paddleocr.json

refactor(paddleocr): migrate from sync API to async Job API (#15967)

2026-06-16 19:34:21 +08:00

perplexity.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

ppio.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

qiniu.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

ragcon.json

Updated RAGcon model provider (go) (#16950)

2026-07-15 20:59:23 +08:00

replicate.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

siliconflow.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

stepfun.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

togetherai.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

tokenhub.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

tokenpony.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

upstage.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

vllm.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

volcengine.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

voyage.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00

xai.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

xiaomi.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

xinference.json

Fix: provider name (#16733)

2026-07-09 10:19:10 +08:00

xunfei.json

feat: populate content_length and max_output from official docs (#17836)

2026-08-05 15:22:57 +08:00

zhipu-ai.json

Go: fix unused check (#17922)

2026-08-06 14:45:10 +08:00