keung67
keung67
### 🥰 需求描述 安全級別 gemini pro 連要他講個笑話也不行... 參考 https://github.com/zuisong/gemini-openai-proxy/blob/main/dist/main_cloudflare-workers.mjs ``` safetySettings: [ HarmCategory.HARM_CATEGORY_HATE_SPEECH, HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT, HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, HarmCategory.HARM_CATEGORY_HARASSMENT ].map((category) => ({ category, threshold: HarmBlockThreshold.BLOCK_NONE })) ``` 是否可以增加参数，将gemini的安全阈值设置为BLOCK_NONE？ https://github.com/soulteary/amazing-openai-api/issues/1 ### 🧐 解决方案 [index.zip](https://github.com/lobehub/lobe-chat/files/14396320/index.zip)...
敏感詞Gemini會出錯，例句"講個笑話"，觸發騷擾安全策略： [GoogleGenerativeAI Error]: Candidate was blocked 但官方 https://gemini.google.com 不會擋 可否 add safetySettings, set block_none 參考： https://github.com/google/generative-ai-python/issues/126#issuecomment-1890443851 https://github.com/google/generative-ai-docs/issues/212 是否可以增加参数，将gemini的安全阈值设置为BLOCK_NONE？ https://github.com/soulteary/amazing-openai-api/issues/1 https://github.com/babaohuang/GeminiProChat/issues/74 https://github.com/lobehub/lobe-chat/issues/1387
as title. Can Support Claude 3 Opus model? Reference: [https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-opus](https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-opus) Anthropic on Vertex AI: https://python.langchain.com/v0.2/docs/integrations/llms/google_vertex_ai_palm/#anthropic-on-vertex-ai Thank you