storageContext + SharePoint
Cut through millions of documents to surface the knowledge that matters
OVERVIEW
Large enterprises accumulate millions of documents across hundreds of SharePoint site collections. Critical knowledge lives in departmental sites, project libraries, and team folders -- separated by organizational boundaries and complex permission structures that make cross-site discovery nearly impossible. Context connects to your SharePoint environment and indexes documents across every site collection, respecting security trimming while enabling knowledge discovery that SharePoint search alone cannot provide. When a compliance officer searches for regulatory guidance, Context surfaces relevant documents from legal, finance, and operations SharePoint sites -- along with the Teams conversations that discussed those policies and the Jira tickets that tracked implementation. Every document, list item, and page becomes a node in your knowledge graph, connected to related knowledge across Confluence, Slack, Microsoft Teams, and every other tool your organization uses. Context deploys on your infrastructure and processes SharePoint content locally. No documents leave your network. Whether you run SharePoint Online, SharePoint Server on-premises, or a hybrid configuration, Context integrates with your existing topology.
KEY CAPABILITIES
Key Capabilities
- 01Cross-site collection document discovery -- search and surface relevant documents from any site collection regardless of organizational hierarchy or departmental boundaries
- 02Permission-aware indexing with SharePoint security trimming -- every search result respects the user's existing SharePoint permissions, ensuring no unauthorized access through the knowledge graph
- 03Deep document extraction for Word, Excel, PowerPoint, and PDF -- extract text, tables, headers, and metadata from Office documents and PDFs stored in document libraries
- 04List and metadata awareness -- index SharePoint list items, custom metadata columns, and managed metadata term sets to enable faceted knowledge discovery
- 05Version history tracking -- capture document evolution over time and connect specific versions to the decisions and conversations that drove changes
- 06Site collection and hub site relationship mapping -- understand the organizational topology of your SharePoint environment and surface knowledge based on site relationships
USE CASES
Use Cases
Regulatory Document Discovery
A compliance team is preparing for a SOC 2 audit and needs to locate all relevant control documentation. Policies live in the Legal SharePoint site, implementation evidence is in Engineering, and training records are in HR. Context searches across all three site collections simultaneously, surfacing the specific documents, their version history, and the Teams conversations where stakeholders discussed policy updates. What used to take weeks of manual document gathering across departments now takes minutes.
M&A Knowledge Integration
After acquiring a company, the integration team needs to understand the acquired organization's processes and documentation. Context indexes the acquired company's SharePoint alongside the parent organization, creating a unified knowledge graph. Engineers can search for "deployment process" and see both the existing runbook and the acquired team's approach, along with Slack discussions comparing the two methodologies. Context accelerates cultural and operational integration by making institutional knowledge instantly discoverable.
Cross-Department Project Coordination
A product launch requires coordination across marketing, engineering, legal, and sales. Each department maintains their launch materials in separate SharePoint sites. Context connects the marketing brief, engineering release notes, legal review documents, and sales enablement materials into a single knowledge view. When the VP of Product asks "what is the status of the privacy review for the EU launch?", Context surfaces the legal team's review document, the engineering ticket tracking GDPR compliance, and the Slack thread where the DPO provided sign-off.
HOW IT WORKS
How It Works
DATA FLOW
SECURITY & COMPLIANCE
Security & Compliance
SOC 2 Type II
GDPR
HIPAA
ISO 27001DEPLOYMENT
Deployment Options
DEPLOYMENT ARCHITECTURE
FREQUENTLY ASKED QUESTIONS
Frequently Asked Questions
Does Context work with SharePoint on-premises?
Yes. Context supports SharePoint Server 2016, 2019, and Subscription Edition on-premises deployments. For on-premises, Context connects via the SharePoint REST API using a service account. Context itself also deploys on your infrastructure, so the entire pipeline runs within your network. Hybrid configurations where some sites are in SharePoint Online and others are on-premises are fully supported.
How does Context handle SharePoint permissions?
Context enforces SharePoint security trimming on every search query. When a user searches Context, results are filtered based on their Azure AD identity and SharePoint permissions. If a user does not have access to a document in SharePoint, they will not see that document or any knowledge extracted from it in Context. Permissions are synced continuously, so access changes in SharePoint are reflected in Context within minutes.
What document formats does Context extract from SharePoint?
Context extracts full text and structure from Word (.docx), Excel (.xlsx), PowerPoint (.pptx), PDF, plain text, and HTML pages. For Excel files, Context indexes cell content, sheet names, and named ranges. For PowerPoint, Context extracts slide text, speaker notes, and embedded tables. OneNote notebooks stored in SharePoint are also supported. Binary or image-only files are logged but not indexed for text content.
Can Context index SharePoint lists and metadata?
Yes. Context indexes SharePoint list items including custom columns, choice fields, and managed metadata term sets. This enables knowledge discovery based on business metadata -- for example, searching for all documents tagged with a specific project code or regulatory framework. List views and calculated columns are captured as additional context.
How does Context handle large SharePoint environments with millions of documents?
Context uses a distributed crawl architecture that processes multiple site collections in parallel. The initial sync is throttle-aware and respects SharePoint API rate limits to avoid impacting your environment. Incremental updates use SharePoint change tokens, which are highly efficient for large environments. Organizations with over 10 million documents typically complete initial indexing within 48 hours and receive real-time updates thereafter.
Does Context support SharePoint hub sites and associated sites?
Yes. Context understands the hub site topology and uses it to enrich knowledge graph relationships. Documents from sites associated with the same hub are given stronger relationship signals, which improves search relevance when users are working within a specific business context. Hub site navigation and shared metadata are also indexed.
SETUP OVERVIEW
Setup Overview
Install the Context SharePoint connector using Helm. Register an Azure AD application with Sites.Read.All permissions for SharePoint Online, or configure a service account for SharePoint Server on-premises. Provide your SharePoint tenant URL (for Online) or farm URL (for on-premises). Context will discover site collections automatically and begin the initial crawl. Configure include or exclude rules to scope indexing to specific site collections if needed. Most organizations complete initial indexing within 24 hours depending on document volume.
RELATED INTEGRATIONS
Related Integrations
Microsoft Teams
Connect Microsoft Teams to Context and extract knowledge from channels, chats, and meeting transcripts. Works with Microsoft 365 and Teams Premium in on-premise deployments.
Confluence
Connect Context to Confluence to link documentation, design decisions, and team knowledge to every tool in your stack. Permission-aware indexing with on-premise deployment.
Google Drive
Connect Google Drive and shared drives to your on-premise knowledge graph. Context extracts full-text content from Docs, Sheets, Slides, and PDFs, linking documents to related conversations and tickets across your organization.
Ready to connect SharePoint?
See Context + SharePoint in action with a 30-minute technical walkthrough tailored to your environment.
BOOK A DEMO