opensource/AstrBot
3
0
Fork 0
mirror of https://github.com/AstrBotDevs/AstrBot.git synced 2026-08-31 01:40:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: update deprecated NVIDIA retrieval models (#9750)

Browse Source 
* fix: update deprecated NVIDIA retrieval models

* Delete tests/test_nvidia_embedding_source.py

* Delete tests/test_nvidia_rerank_source.py

---------

Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com>
This commit is contained in:
C10H14N2O5
2026-08-21 17:17:56 +08:00
committed by GitHub
parent 4fe2975975
commit b0bb3b4760
3 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
astrbot/core/config/default.py
+3 -3
View File
@@ -1904,9 +1904,9 @@ CONFIG_METADATA_2 = {
"enable": True,
"embedding_api_key": "",
"embedding_api_base": "https://integrate.api.nvidia.com/v1",
"embedding_model": "nvidia/llama-nemotron-embed-1b-v2",
"embedding_model": "nvidia/nemotron-3-embed-1b",
"input_type": "passage",
"embedding_dimensions": 1024,
"embedding_dimensions": 2048,
"timeout": 20,
"proxy": "",
},
@@ -1982,7 +1982,7 @@ CONFIG_METADATA_2 = {
"enable": True,
"nvidia_rerank_api_key": "",
"nvidia_rerank_api_base": "https://ai.api.nvidia.com/v1/retrieval",
"nvidia_rerank_model": "nv-rerank-qa-mistral-4b:1",
"nvidia_rerank_model": "nvidia/llama-nemotron-rerank-vl-1b-v2",
"nvidia_rerank_model_endpoint": "/reranking",
"timeout": 20,
"nvidia_rerank_truncate": "",
astrbot/core/provider/sources/nvidia_embedding_source.py
+1 -1
View File
@@ -28,7 +28,7 @@ class NvidiaEmbeddingProvider(EmbeddingProvider):
)
self.timeout = int(provider_config.get("timeout", 20))
self.model = provider_config.get(
"embedding_model", "nvidia/llama-nemotron-embed-1b-v2"
"embedding_model", "nvidia/nemotron-3-embed-1b"
)
self.input_type = provider_config.get("input_type", "passage")
astrbot/core/provider/sources/nvidia_rerank_source.py
+1 -1
View File
@@ -19,7 +19,7 @@ class NvidiaRerankProvider(RerankProvider):
).rstrip("/")
self.timeout = provider_config.get("timeout", 20)
self.model = provider_config.get(
"nvidia_rerank_model", "nv-rerank-qa-mistral-4b:1"
"nvidia_rerank_model", "nvidia/llama-nemotron-rerank-vl-1b-v2"
)
self.model_endpoint = provider_config.get(
"nvidia_rerank_model_endpoint", "/reranking"