为您的代码库提供实时索引：安全、个人化、可扩展

TL;DR: At Augment, we built a secure, personalized code indexing system that:

TL;DR：在 Augment，我们构建了一个安全、个性化的代码索引系统，具备以下特点：

Updates within seconds of code changes (vs. competitors' 10-minute delays)
代码变更后数秒内即可更新（而竞争对手需延迟 10 分钟）
Uses custom AI models instead of generic embeddings
使用自定义 AI 模型而非通用 embedding
Processes thousands of files/second using Google Cloud
借助 Google Cloud 每秒处理数千个文件
Maintains separate indices per developer to handle branch switching
为每位开发者维护独立索引，以应对分支切换
Implements strict security with proof-of-possession and no third-party APIs
通过持有证明实现严格安全，且不使用任何第三方 API
Efficiently manages RAM usage by sharing overlapping indices between users
通过共享重叠索引在用户间高效管理内存使用

The result: Context-aware AI that actually keeps up with real development workflows while protecting code security.

结果：能够真正跟上真实开发工作流、同时保护代码安全的上下文感知 AI。

A different approach to retrieval

另一种检索思路

The dominant approach in retrieval remains calling generic model APIs, like OpenAI, to create embeddings for snippets of code files and documents, and then using embedding search APIs, like Pinecone, to retrieve snippets related to the query. However, this approach leads to poor quality, poor latency, and potentially even poor security.

当前检索领域的主流做法仍是调用通用模型 API（如 OpenAI）为代码文件和文档片段生成 embedding，然后再通过 embedding 搜索 API（如 Pinecone）检索与查询相关的片段。然而，这种做法会导致质量差、延迟高，甚至可能带来安全隐患。

Therefore, Augment has taken a different approach: We have developed an indexing and embedding search system tailored to give you the most relevant and up-to-date context across all our products.

因此，Augment 采取了不同的做法：我们开发了一套索引与 embedding 搜索系统，专门为你提供最相关、最新的上下文，覆盖我们所有产品。

A personal index for each developer

为每位开发者建立个人索引

All of our products understand your codebase. But what is actually “your codebase”? In the real world, this is a surprisingly tricky question.

我们所有的产品都能理解你的代码库。但“你的代码库”到底指什么？在现实世界中，这是一个出人意料的棘手问题。

Personal index for each developer

Consider the scenario that you have just received a comment on one of your pull requests asking you to rename a function. You want to address the comment quickly and move on. So y...