binary-husky
[Feature]: 请问现在版本支持本地部署的deepseek吗，有的话如何配置
修改config or private_config文件。如果是ollama部署，AVAIL_LLM_MODELS可以增加ollama-deepseek-r1:671b，就可以了。远程的话做一个映射API_URL_REDIRECT = {"http://localhost:11434/api/chat": "http://{IP}:{PORT}/api/chat"}。就是这个展示界面有点不舒服，think内容和回答内容混在一起。
修改config or private_config文件。如果是ollama部署，AVAIL_LLM_MODELS可以增加ollama-deepseek-r1:671b，就可以了。远程的话做一个映射API_URL_REDIRECT = {"http://localhost:11434/api/chat": "http://{IP}:{PORT}/api/chat"}。就是这个展示界面有点不舒服，think内容和回答内容混在一起。
非常感谢
如何调用 阿里的deepseek-r1？ 老哥
把DASHSCOPE_API_KEY填上，然后修改 API_URL_REDIRECT = {"https://api.deepseek.com/v1/chat/completions": "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions"}
注：未经测试，参考https://help.aliyun.com/zh/model-studio/developer-reference/deepseek
如何调用 阿里的deepseek-r1？ 老哥
把DASHSCOPE_API_KEY填上，然后修改 API_URL_REDIRECT = {"https://api.deepseek.com/v1/chat/completions": "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions"}
注：未经测试，参考https://help.aliyun.com/zh/model-studio/developer-reference/deepseek
您好，我已经按照您的建议修改了，但是切换到deepseek-r1模型时还是报错，请问这些操作具体该怎么做呢？
修改步骤： 1、config.py
LLM_MODEL = "deepseek-r1" # 可选 ↓↓↓ AVAIL_LLM_MODELS = ["qwen-max", "o1-mini", "o1-mini-2024-09-12", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12", "gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo", "gemini-1.5-pro", "chatglm3", "chatglm4", "deepseek-chat", "deepseek-coder", "deepseek-reasoner","deepseek-r1" ] 2、request_llms/bridge_all.py
-=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
qwen_models = ["qwen-max-latest", "qwen-max-2025-01-25","qwen-max","qwen-turbo","qwen-plus","deepseek-r1"] if any(item in qwen_models for item in AVAIL_LLM_MODELS): try: from .bridge_qwen import predict_no_ui_long_connection as qwen_noui from .bridge_qwen import predict as qwen_ui model_info.update({ "qwen-turbo": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 100000, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, "qwen-plus": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 129024, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, "qwen-max": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 30720, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, "qwen-max-latest": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 30720, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, "qwen-max-2025-01-25": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 30720, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, "deepseek-r1": { "fn_with_ui": qwen_ui, "fn_without_ui": qwen_noui, "can_multi_thread": True, "endpoint": None, "max_token": 30720, "tokenizer": tokenizer_gpt35, "token_cnt": get_token_num_gpt35, }, }) except: logger.error(trimmed_format_exc())