Skip to main content

​
Frequently Asked Questions

Common questions and answers about using FLTR.

​
General

FLTR is a Context as a Service platform that makes your documents AI-ready. It provides semantic search over your content using hybrid vector + keyword search, accessible via REST API or Model Context Protocol (MCP).
FLTR serves three main audiences:
  • AI Developers - Building RAG applications, knowledge bases, and AI agents
  • No-Code Builders - Integrating with Zapier, Make, n8n
  • Enterprises - Team collaboration with advanced security
FLTR combines:
  • Hybrid search - Vector similarity + keyword matching
  • MCP-native - Built for Claude Desktop, VS Code, Cursor
  • Simple API - RESTful with comprehensive docs
  • Multimodal - PDFs, images, text, code
The FLTR API is proprietary, but we provide:
  • Open API specification (OpenAPI 3.1)
  • Public documentation
  • Example integrations on GitHub
  • MCP server implementations

​
Pricing & Billing

Yes! Free tier includes:
  • 50 requests/hour (anonymous)
  • 2 datasets
  • 100 documents
  • 1GB storage
Paid plans start at $29/month.
Billing is credit-based:
  • Queries: 1 credit per query
  • Uploads: 10 credits per document
  • Storage: 1 credit per GB per month
  • Reranking: +2 credits per query
Plans include monthly credit allocations.
Yes, anytime. Changes take effect immediately with prorated billing.
We accept:
  • Credit/debit cards (Stripe)
  • ACH (US only)
  • Wire transfer (Enterprise)
  • Annual prepayment (10% discount)

​
Technical

We support:
  • Documents: PDF, DOCX, PPTX, TXT, MD
  • Images: JPG, PNG (with OCR)
  • Code: PY, JS, JAVA, etc.
  • Data: JSON, XML, CSV, YAML
Max file size: 10MB
Processing time depends on file size:
  • Text (< 1MB): 1-5 seconds
  • PDFs (1-5MB): 5-15 seconds
  • Large PDFs (5-10MB): 15-30 seconds
  • Images: +5-10 seconds for OCR
Default: text-embedding-3-small (OpenAI)Coming soon:
  • text-embedding-3-large
  • Custom models (Enterprise)
  • Multilingual models
Not yet. Custom embedding models are planned for Enterprise plans. Contact sales to discuss.
Hybrid search provides:
  • Precision: 85-95% for exact matches
  • Recall: 80-90% for semantic queries
  • With reranking: +5-10% improvement
Accuracy depends on document quality and metadata.
Not directly. You need to query each dataset separately. Use batch queries to search multiple datasets efficiently.Multi-dataset search is on our roadmap for future release.

​
Security & Privacy

Yes. FLTR implements:
  • Encryption: TLS 1.3 in transit, AES-256 at rest
  • Isolation: Data separated by account
  • Access control: Role-based permissions
  • Compliance: SOC 2 Type II (in progress)
Only you and users you grant access to. FLTR staff cannot access your documents unless you explicitly grant support access for troubleshooting.
Data is stored in:
  • US East (primary): us-east-1 (AWS)
  • EU (optional): eu-west-1 (AWS)
Enterprise plans can choose region.
No. Your data is never used for:
  • Model training
  • Research
  • Analytics (except aggregated usage stats)
  • Any purpose outside your use case
Yes. You can:
  • Delete documents anytime
  • Delete datasets (removes all documents)
  • Delete account (removes all data within 30 days)
Backups are retained for 30 days, then permanently deleted.
Yes. FLTR is GDPR compliant with:
  • Data processing agreements
  • Right to deletion
  • Data portability
  • Privacy by design

​
Integration

Three ways:
  1. REST API - For any language
  2. MCP - For Claude Desktop, VS Code, Cursor
  3. No-code - Zapier, Make, n8n
See Getting Started.
Not yet. We’re working on official SDKs for:
  • Python
  • JavaScript/TypeScript
  • Go
For now, use the REST API directly.
Yes! FLTR has native MCP support for Claude Desktop.See OAuth Setup for configuration.
Yes, use FLTR as a retriever in LangChain:
See our LangChain integration guide.
No. FLTR is a managed service only.Enterprise plans include:
  • Dedicated infrastructure
  • Custom domains
  • VPC peering

​
Support

Support varies by plan:
  • Free: Email support (48h response)
  • Pro: Email + chat (24h response)
  • Enterprise: Priority support + Slack (4h response)
Coming soon. We’re setting up a public status page for real-time service health monitoring.It will include:
  • Email notifications
  • SMS alerts
  • Slack integration
Report bugs via:Include:
  • Steps to reproduce
  • Expected vs actual behavior
  • Request/response examples
Yes! We love feedback. Request features via:We prioritize based on user demand.

​
Still Have Questions?

Email Support

support@fltr.com

Documentation

Browse complete docs

Contact Sales

Schedule a demo

Troubleshooting

Common issues and fixes