Power real-time applications and agents with Document Intelligence
https://www.databricks.com/blog/power-real-time-applications-and-agents-document-intelligence📌 Databricks文件智慧API轉正式版，解析、分類、擷取一次打包
TL;DR：Databricks將文件解析、分類、擷取REST API轉為正式版，讓應用與agent即時把文件轉成結構化資料。
Databricks指出，其企業客戶每天收到的文件數以百萬計。這些文件裡藏著營運、客戶、財務的關鍵脈絡，卻長期卡在同一個瓶頸：文件進來之後，得先有人讀過、把重點手動抄出來，才能進入下游的商業分析或決策流程。隨著文件量成長，這個人工環節的延遲與成本只會跟著放大。
🤔 人工讀文件，正是downstream決策的瓶頸
無論是發票核對、合約審查還是客服單據歸類，表面上是不同的工作流程，卻共享同一個卡點：在資料能被拿去做分析或決策之前，必須先有人把非結構化文件讀懂、拆解成可用的欄位。這一步沒有自動化,整條管線就動不了。
🧩 Parsing、分類、擷取三合一，決策路由API搶先測試
Databricks宣布，用於解析（parsing）、分類（classification）、擷取（extraction）的文件智慧REST API現已正式上線（Generally Available）；另外新增一支用於文件路由的決策（decisions）REST API，目前為beta測試階段。開發者可以在文件抵達的當下呼叫這些API，讓工作流程自動判斷「這份文件是什麼」、拉出需要的細節，再把結果交給對的人或對的agent接手下一步。
💻 從發票擷取欄位到律師審約，一個REST呼叫搞定
Databricks舉例，可用ai_extract REST API從發票中擷取欄位。這類即時文件理解能力也能直接嵌入既有的工作場域：在Databricks Apps中，可以打造一個合約收件流程，讓律師上傳合約後，開啟審核表單時關鍵條款已經自動填好。除了這種人機協作（human-in-the-loop）的互動式應用，這些API也能被架在Agent Bricks上的自訂agent呼叫,在agent需要理解或分析收到的文件、再決定下一步動作時使用。Databricks也提供以Genie Code輸入prompt來建置此類工作流程的方式，或直接參考REST API文件與解析、分類、擷取各自的操作指南。
🎯 給正在建置文件工作流程的工程師
如果你的團隊正苦於為合約、發票、客服單據之類的文件自建擷取管線，這類平臺內建的REST API提供了一條直接整合進既有應用或agent決策流程的路徑，不必從零打造文件理解模型，但實際擷取精準度與延遲表現仍需依自身文件類型實測評估。
🔗 來源
- 標題：Power real-time applications and agents with Document Intelligence
- 作者／機構：Databricks
- 連結：https://www.databricks.com/blog/power-real-time-applications-and-agents-document-intelligence
#DocumentIntelligence #Databricks #AgentBricks #RESTAPI #DocumentProcessing #AIAgents #DataExtraction #EnterpriseAI #Automation #LLMOps
原始資料 Databricks · 收集於 2026-10-14
摘要原文
At Databricks, our enterprise customers receive millions of documents every single day. These messy, unstructured documents hold critical context about operations, customers, and finances that power key downstream decisions across the business. Yet when a document arrives, putting that enterprise context to work is surprisingly tedious. For example: These are distinct workflows, but they share the same bottleneck : before customers can use the valuable data inside the documents for business analytics or decision-making, someone has to read each document and pull out what matters. That manual step slows everything downstream, and the bottleneck and costs explode as the incoming document volume grows. Today, the Document Intelligence REST APIs for parsing, classification, and extraction are Generally Available. Our decisions REST API , great for document routing, is launched in beta. Developers can call these APIs from an application or agent when a document arrives, so the workflow can identify what came in, pull out the details it needs, and put them in front of the right person or agent for next steps. These APIs transform your documents into structured insights in real-time: Example using the ai_extract REST API to extract fields from an invoice: You can use the REST APIs to bring document understanding into the application where work already happens. For example, with Databricks Apps, you can build a contract intake flow where a lawyer uploads an agreement and opens a review form with the key terms already filled in: Interactive, human-in-the-loop applications are just one way to leverage real-time document processing. You can also call these APIs from a custom agent built on Agent Bricks when it needs to understand or analyze incoming documents before making its next decision. Want to build a workflow like this? Open Genie Code in your Databricks workspace and start typing your prompt: You can also build directly with the REST API reference and the guides for parsing , classification , and extraction : Subscribe to our blog and get the latest posts delivered to your inbox.
由 claude-code/sonnet 自動生成