大模型
website ·
Weaviate Ask Mode 新增结果评估开关
Weaviate Ask Mode 新增结果评估开关，允许用户在快速廉价答案与可验证来源之间权衡。可设置评估为“none”以跳过评估，或设为“llm”以额外调用模型评估答案并保留相关来源，同时提供部分答案和缺失信息信号。
AI推荐理由 该功能为RAG应用提供了灵活性与可验证性的平衡控制，对优化查询成本和提升答案可靠性有实际帮助。
86
浏览 895
点赞 8
评论 2
转发 3
正文
跳过评估，获得更快、更便宜的答案。
或者获得与你的答案匹配的精确来源集。
现在你可以完全控制延迟和可验证性。
𝗔𝘀𝗸 𝗠𝗼𝗱𝗲将自然语言问题转化为对Weaviate Cloud集合的搜索或聚合，然后生成基于检索数据的答案。
以前，结果评估步骤总是运行。现在你可以自定义ask mode运行的行为，使用Python中的𝗿𝗲𝘀𝘂𝗹𝘁\_𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻或JavaScript/TypeScript中的𝗿𝗲𝘀𝘂𝗹𝘁𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻：
- 将其设置为“𝘯𝘰𝘯𝘦”以检索数据并生成最终答案。这是默认的、更快更便宜的工作流程。
- 将其设置为“𝘭𝘭𝘮”以使用额外的模型调用评估答案与检索到的上下文。这保留了与答案相关或使用的来源，并报告可能的不完整或缺失信息。
工作流程变为：
1. 检索数据
2. 生成答案
3. 可选地评估答案并完善其来源
由于评估需要额外的LLM调用，它增加了延迟和成本。但它也启用了额外字段：𝘪𝘴\_𝘱𝘢𝘳𝘵𝘪𝘢𝘭\_𝘢𝘯𝘴𝘸𝘦𝘳和𝘮𝘪𝘴𝘴𝘪𝘯𝘨\_𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘰𝘯，为你提供关于答案是否完整以及可能缺失什么的有用信号。
你现在可以为每个应用选择正确的权衡：当不需要来源细化时，获得更快的响应；或者当完整性信号重要时，进行额外的评估[docs.weaviate.io/query-agent/gu…](https://docs.weaviate.io/query-agent/guides/ask_mode?utm_source=channels&utm_medium=w_social&utm_campaign=agents&utm_content=diagram_post_680322779)。
阅读Ask Mode文档：
查看原文（中文正文为 AI 翻译）
Skip the evaluation and get a faster, cheaper answer.
Or get a precise set of sources that match your answer.
Now you have full control between latency and verifiability.
𝗔𝘀𝗸 𝗠𝗼𝗱𝗲 turns a natural-language question into searches or aggregations across your Weaviate Cloud collections, then generates an answer grounded in the retrieved data.
Previously, the result evaluation step always ran. Now you can customise the behavior of your ask mode run, using 𝗿𝗲𝘀𝘂𝗹𝘁\_𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 in Python or 𝗿𝗲𝘀𝘂𝗹𝘁𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 in JavaScript/TypeScript:
- Set it to "𝘯𝘰𝘯𝘦" to retrieve data and generate the final answer. This is the default, faster and cheaper workflow.
- Set it to "𝘭𝘭𝘮" to evaluate the answer against the retrieved context using an additional model call. This retains the sources relevant to or used in the answer, and report possible incompleteness or missing information.
The workflow becomes:
1. Retrieve data
2. Generate an answer
3. Optionally evaluate the answer and refine its sources
Since the evaluation requires an additional LLM call, it adds latency and cost. But it also enables extra fields: 𝘪𝘴\_𝘱𝘢𝘳𝘵𝘪𝘢𝘭\_𝘢𝘯𝘴𝘸𝘦𝘳 and 𝘮𝘪𝘴𝘴𝘪𝘯𝘨\_𝘪𝘯𝘧𝘰𝘳𝘮𝘢𝘵𝘪𝘰𝘯, giving you useful signals about whether the answer is complete and what may still be missing.
You can now choose the right tradeoff for each application: faster responses when source refinement isn't required, or additional evaluation when [docs.weaviate.io/query-agent/gu…](https://docs.weaviate.io/query-agent/guides/ask_mode?utm_source=channels&utm_medium=w_social&utm_campaign=agents&utm_content=diagram_post_680322779)eness signals matter.
Read the Ask Mode documentation:
