config: set default judge_model=gpt-5, embedding_model=text-embedding-3-small

gpt-5.4/5.5/5.2/5.4-mini/5.4-nano are incompatible with RAGAS 0.4.3
because they require max_completion_tokens instead of max_tokens.
gpt-5 / gpt-4.1 support max_tokens and json_object mode required by RAGAS.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
2026-06-23 15:29:01 +08:00
parent 2ad2c1ea9d
commit a781ba1e4a
4 changed files with 8 additions and 6 deletions

View File

@@ -8,8 +8,10 @@ OPENAI_BASE_URL=http://6.86.80.4:30080/v1
OPENAI_TIMEOUT_SECONDS=180
# 默认评测模型(可在场景 YAML 或 Web 控制台 LLM 配置中覆盖)
RAGAS_JUDGE_MODEL=deepseek-v4-flash
RAGAS_EMBEDDING_MODEL=text-embedding-v3
# RAGAS_JUDGE_MODEL 需支持 max_tokens + json_objectgpt-5、gpt-4.1、gpt-4o 等)
# 注意gpt-5.4/5.5/5.2 系列不支持 max_tokens与 RAGAS 0.4.3 不兼容
RAGAS_JUDGE_MODEL=gpt-5
RAGAS_EMBEDDING_MODEL=text-embedding-3-small
# 评估并发控制(启用 7 个指标时建议 RAGAS_METRIC_TIMEOUT_SECONDS=300
BATCH_SIZE=8