AlexStocks commented on code in PR #932: URL: https://github.com/apache/dubbo-go-samples/pull/932#discussion_r2386512244
########## llm/.env.example: ########## @@ -38,25 +34,23 @@ NACOS_URL = nacos://localhost:8848 TIME_OUT_SECOND = 300 MAX_CONTEXT_COUNT = 3 -# Example configurations for different providers: +# Example configurations for different scenarios: # -# OpenAI: +# Scenario 1: Multiple models from same provider (current approach) +# LLM_MODELS = gpt-4, gpt-3.5-turbo, gpt-4-turbo # LLM_PROVIDER = openai -# LLM_MODELS = gpt-4, gpt-3.5-turbo # LLM_BASE_URL = https://api.openai.com/v1 # LLM_API_KEY = your-openai-api-key # MODEL_NAME = gpt-4 # -# Anthropic: -# LLM_PROVIDER = anthropic -# LLM_MODELS = claude-3-sonnet-20240229, claude-3-haiku-20240307 -# LLM_BASE_URL = https://api.anthropic.com/v1 -# LLM_API_KEY = your-anthropic-api-key -# MODEL_NAME = claude-3-sonnet-20240229 -# -# Azure OpenAI: -# LLM_PROVIDER = azure-openai -# LLM_MODELS = gpt-4, gpt-35-turbo -# LLM_BASE_URL = https://your-resource.openai.azure.com/openai/deployments/your-deployment -# LLM_API_KEY = your-azure-openai-api-key +# Scenario 2: Multiple models from different providers (future enhancement) +# LLM_MODELS = gpt-4, claude-3-sonnet, llava:7b +# LLM_PROVIDER = mixed # MODEL_NAME = gpt-4 +# # Each model would have its own configuration in the future +# +# Scenario 3: Local models with different endpoints Review Comment: LLMConfig{ Model: model, Provider: config.LLMProvider, BaseURL: config.LLMBaseURL, APIKey: config.LLMAPIKey, } 你这个配置和这个 config 对不上，感觉 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
