Technical blog on how we built SmithDB (our database purpose built for agent traces)
Harrison Chase(@hwchase17)106 字 (约 1 分钟)
85
SmithDB 是为代理追踪设计的数据库，通过对象存储实现高效全文搜索索引。
入选理由：SmithDB 使用对象存储构建全文搜索索引，降低 GET 请求成本。
FeaturedTweet#数据库#全文搜索#LangChain#对象存储英文
产品
什么是 SmithDB？
为代理追踪设计的数据库，支持高效全文搜索索引。
为什么现在值得关注？
最近变化
2026-06-25 · SmithDB 使用对象存储构建全文搜索索引，降低 GET 请求成本。
SmithDB 被反复提及时，通常意味着它正在影响产品路线、开发者工作流或 AI 产业判断。这个页面把分散材料合并成一个可持续更新的观察入口。
如果只读 3 篇
Technical blog on how we built SmithDB (our database purpose built for agent traces)
Harrison Chase(@hwchase17) · 8.5 分
@ankush_gola11 Missed Part 1? Here’s how we built a custom inverted index from scratch for SmithDB...
LangChain(@LangChainAI) · 8.5 分
The next phase of LangSmith is more than faster trace loading. We’re making trace data more useful. ...
LangChain(@LangChainAI) · 6.8 分
📰 SmithDB 最新动态
已收录 8 篇与「SmithDB」相关的 AI 资讯和分析。
@ankush_gola11 Missed Part 1? Here’s how we built a custom inverted index from scratch for SmithDB...
LangChain(@LangChainAI)71 字 (约 1 分钟)
85
LangChain 介绍了如何从零开始构建一个自定义的倒排索引，用于 SmithDB 的全文搜索功能。
入选理由：倒排索引是实现 SmithDB 全文搜索的核心机制。
FeaturedTweet#LangChain#倒排索引#SmithDB#全文搜索英文
LangChain Announces Next Phase of LangSmith: SmithDB Foundation Layer for Enhanced Trace Data Utility
LangChain(@LangChainAI)150 字 (约 1 分钟)
68
LangSmith's next phase introduces SmithDB as the foundational layer to improve trace data utility beyond just loading speed, marking an architectural upgrade for agent observability announced officially by LangChain.
入选理由：SmithDB是LangSmith新阶段的基础数据层，专为agent可观测性设计
FeaturedTweet#LangSmith#SmithDB#Agent Observability#LangChain英文
first in a series of technical blogs of how we build llm infra
Harrison Chase(@hwchase17)107 字 (约 1 分钟)
65
文章介绍了如何构建支持大语言模型基础设施的倒排索引，以实现高效搜索和过滤。
入选理由：SmithDB 使用自定义倒排索引实现高效搜索。
FeaturedTweet#LLM#数据库#搜索#LangChain英文
SmithDB lets you see traces in seconds instead of minutes.
LangChain(@LangChainAI)132 字 (约 1 分钟)
65
SmithDB provides second-level trace capabilities, significantly improving system observability.
入选理由：SmithDB 能在几秒钟内展示追踪信息，而不是几分钟。
FeaturedTweet#SmithDB#Observability#Trace System英文
ICYMI: SmithDB is our purpose-built data layer for agent observability + eval workloads
LangChain(@LangChainAI)160 字 (约 1 分钟)
45
LangChain launches SmithDB, a self-hosted data layer purpose-built for agent observability and evaluation workloads, supporting low-latency complex queries over large traces with multi-cloud deployment.
入选理由：SmithDB 针对 Agent 可观测性场景设计，解决传统数据库难以处理大规模 Trace 复杂查询的问题
FeaturedTweet#LangChain#Agent#Observability#Database#SmithDB英文
Which Was Your Favorite Launch?
Harrison Chase(@hwchase17)92 字 (约 1 分钟)
45
Harrison Chase launched a poll asking users to choose between SmithDB and LangSmith Engine, a purpose-built database for agent trace data and an AI agent that optimizes other agents using trace data, respectively.
入选理由：SmithDB 是专为存储和管理智能体（agent）追踪数据构建的数据库。
FeaturedTweet#LangChain#AI Agent#Database#SmithDB中英混合
Behind the scenes of SmithDB
LangChain(@LangChainAI)86 字 (约 1 分钟)
35
SmithDB uses Apache DataFusion as its query engine, optimizing specific workloads and storage backend performance through custom execution plans. This is LangChain's key technical choice in building SmithDB, and DataFusion's Rust foundation and extensibility simplified the development process.
入选理由：SmithDB采用Apache DataFusion作为底层查询引擎
FeaturedTweet#SmithDB#Apache DataFusion#Rust#Query Engine#LangChain英文
🔗 相关术语
与「SmithDB」经常一起出现的 AI 术语。
💡 想追踪「SmithDB」的长期趋势？去 实体雷达 · SmithDB 查看详细分析和跨材料问答。