zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-08 16:38:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
## Summary

- Verify and populate `content_length` (context window) and `max_output`
(max generation tokens) for all **478 chat/vision models** across **47
provider configs**
- Data sourced from **official API documentation** via 12 parallel
agents + targeted web verification
- Update Go test assertions to match verified values

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
jay77721
2026-08-05 15:22:57 +08:00
committed by GitHub
parent 310275208b
commit 47ecc2a231
48 changed files with 927 additions and 450 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
conf/models/nvidia.json
View File

@@ -13,7 +13,8 @@
"models": [
{
"name": "deepseek-ai/deepseek-v4-flash",
"max_tokens": 1048576,
"content_length": 1048576,
"max_output": 393216,
"model_types": [
"chat"
],
@@ -23,7 +24,8 @@
},
{
"name": "deepseek-ai/deepseek-v4-pro",
"max_tokens": 1048576,
"content_length": 1048576,
"max_output": 393216,
"model_types": [
"chat"
],
@@ -33,14 +35,16 @@
},
{
"name": "google/diffusiongemma-26b-a4b-it",
"max_tokens": 8192,
"content_length": 262144,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "google/gemma-4-31b-it",
"max_tokens": 131072,
"content_length": 262144,
"max_output": 262144,
"model_types": [
"chat"
],
@@ -50,21 +54,24 @@
},
{
"name": "meta/llama-3.1-70b-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "meta/llama-3.1-8b-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "meta/llama-3.2-11b-vision-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat",
"vision"
@@ -72,21 +79,24 @@
},
{
"name": "meta/llama-3.2-1b-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "meta/llama-3.2-3b-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "meta/llama-3.2-90b-vision-instruct",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat",
"vision"
@@ -97,28 +107,32 @@
},
{
"name": "meta/llama-3.3-70b-instruct",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "meta/llama-guard-4-12b",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "minimaxai/minimax-m3",
"max_tokens": 8192,
"content_length": 1048576,
"max_output": 16384,
"model_types": [
"chat"
]
},
{
"name": "mistralai/mistral-medium-3.5-128b",
"max_tokens": 131072,
"content_length": 262144,
"max_output": 262144,
"model_types": [
"chat",
"vision"
@@ -129,7 +143,8 @@
},
{
"name": "mistralai/mistral-nemotron",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 131072,
"model_types": [
"chat"
],
@@ -139,7 +154,8 @@
},
{
"name": "moonshotai/kimi-k2.6",
"max_tokens": 262144,
"content_length": 262144,
"max_output": 131072,
"model_types": [
"chat",
"vision"
@@ -150,14 +166,16 @@
},
{
"name": "nvidia/ising-calibration-1.5-31b",
"max_tokens": 8192,
"content_length": 8192,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "nvidia/llama-3.1-nemotron-nano-8b-v1",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -167,7 +185,8 @@
},
{
"name": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat",
"vision"
@@ -175,7 +194,8 @@
},
{
"name": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -185,7 +205,8 @@
},
{
"name": "nvidia/llama-3.3-nemotron-super-49b-v1",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -195,7 +216,8 @@
},
{
"name": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -216,7 +238,8 @@
},
{
"name": "nvidia/nemotron-3-nano-30b-a3b",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -226,7 +249,8 @@
},
{
"name": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat",
"vision"
@@ -241,7 +265,8 @@
},
{
"name": "nvidia/nemotron-3-super-120b-a12b",
"max_tokens": 131072,
"content_length": 262144,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -251,21 +276,24 @@
},
{
"name": "nvidia/nemotron-3-ultra-550b-a55b",
"max_tokens": 8192,
"content_length": 262144,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "nvidia/nemotron-3.5-content-safety",
"max_tokens": 8192,
"content_length": 8192,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "nvidia/nemotron-mini-4b-instruct",
"max_tokens": 4096,
"content_length": 8192,
"max_output": 4096,
"model_types": [
"chat"
],
@@ -275,7 +303,8 @@
},
{
"name": "nvidia/nemotron-nano-12b-v2-vl",
"max_tokens": 8192,
"content_length": 8192,
"max_output": 8192,
"model_types": [
"chat",
"vision"
@@ -297,7 +326,8 @@
},
{
"name": "nvidia/nvidia-nemotron-nano-9b-v2",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 8192,
"model_types": [
"chat"
],
@@ -307,14 +337,16 @@
},
{
"name": "nvidia/riva-translate-4b-instruct-v2",
"max_tokens": 8192,
"content_length": 8192,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "openai/gpt-oss-120b",
"max_tokens": 131072,
"content_length": 131072,
"max_output": 131072,
"model_types": [
"chat"
],
@@ -324,35 +356,40 @@
},
{
"name": "openai/gpt-oss-20b",
"max_tokens": 8192,
"content_length": 131072,
"max_output": 131072,
"model_types": [
"chat"
]
},
{
"name": "poolside/laguna-xs-2.1",
"max_tokens": 8192,
"content_length": 262144,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "stepfun-ai/step-3.7-flash",
"max_tokens": 8192,
"content_length": 32768,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "thinkingmachines/inkling",
"max_tokens": 8192,
"content_length": 8192,
"max_output": 8192,
"model_types": [
"chat"
]
},
{
"name": "z-ai/glm-5.2",
"max_tokens": 8192,
"content_length": 1000000,
"max_output": 128000,
"model_types": [
"chat"
]