@talonic/docs 0.20.2 → 0.20.4

package/dist/seo.d.ts

@@ -26,6 +26,18 @@ declare const API_FAQ: {
     question: string;
     answer: string;
 }[];
+declare const SDK_NAV_SECTIONS: NavSection[];
+declare const MCP_NAV_SECTIONS: NavSection[];
+declare const SDK_SECTION_META: SectionMeta[];
+declare const MCP_SECTION_META: SectionMeta[];
+declare const SDK_FAQ: {
+    question: string;
+    answer: string;
+}[];
+declare const MCP_FAQ: {
+    question: string;
+    answer: string;
+}[];
 declare const PLATFORM_FAQ: {
     question: string;
     answer: string;
@@ -33,4 +45,4 @@ declare const PLATFORM_FAQ: {
 declare const LLMS_TXT = "# Talonic\n\n> AI-powered document structuring platform that turns unstructured files into schema-validated, provenance-tracked structured data.\n\nTalonic ingests documents in 25+ formats (PDFs, scans, images, spreadsheets, emails, archives), discovers every data field through AI extraction and semantic clustering, and produces structured datasets with per-cell confidence scores, reasoning traces, and source provenance. It runs a single deployable stack with Postgres + pgvector, Anthropic Claude for extraction, and Mistral Document AI for OCR.\n\n## How It Works\n\n1. **Upload** \u2014 Drag files/folders into Inputs or ingest via API. ZIP archives unpack automatically. Files are deduplicated via SHA-256 hashing.\n2. **Extract** \u2014 Each document goes through Document AI OCR (converts to Markdown), classification against a 529-type ontology, and AI field extraction (discovers every data point with confidence and source text).\n3. **Build Schema** \u2014 Extracted fields resolve into the Field Registry (canonical names, semantic clusters, master instructions). Define a user template selecting the fields you need.\n4. **Run Job** \u2014 A 4-phase pipeline fills every cell in a documents \u00D7 fields grid. ~30% filled instantly from graph matches, ~70% from AI agents.\n5. **Deliver** \u2014 Push approved data to webhooks, REST APIs, SFTP, email, or S3/R2 cloud storage.\n\n## Sources & Documents\n\nSupported formats across three processing paths:\n- **Text fast-path** (direct read): TXT, MD, HTML, XML, JSON, EML, CSV\n- **AI Vision** (multimodal): PNG, JPG, JPEG, GIF, WEBP\n- **OCR** (Mistral Document AI \u2192 Markdown): PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, XLSM, MSG, BMP\n- **Archives**: ZIP (recursive unpack)\n\nUpload methods: drag-and-drop UI, folder upload (preserves file paths), API upload (single, batch up to 200 files, or archive up to 500 MB). Batch mode available at 50% cost with 48-hour delivery window.\n\nEvery document is classified into a canonical type from the 529-type ontology (e.g., \"Employment Contract\", \"Invoice\", \"Bill of Lading\"). Classification is language-agnostic \u2014 a German Arbeitsvertrag maps to the same type as an English Employment Contract. Unresolvable documents get \"Unclassified Document\".\n\nDocument detail tabs: Raw Extraction (every field with confidence), Resolved Data (mapped to registry), Processing Log (per-stage timing), Original File.\n\n## Field Registry\n\nThe unified knowledge graph of all canonical fields, growing smarter with every document processed.\n\n- **Tier 1 (Core)**: Universal fields across many document types. Most reliable.\n- **Tier 2 (Established)**: Promoted from Tier 3 after frequency thresholds. Production-ready.\n- **Tier 3 (Emerging)**: Newly discovered from a few documents. May promote as more data arrives.\n\nFields with similar meanings cluster automatically via AI embeddings (e.g., \"Vendor Name\", \"Supplier Name\", \"Company Name\" \u2192 same cluster). Master instructions are AI-synthesized extraction directives that improve accuracy over time.\n\n## Schemas\n\nTwo types: **Generated schemas** (auto-created per document type from Tier 1+2 fields) and **User templates** (user-defined output structures).\n\nTemplate workflow: name it \u2192 add fields (display name, data type, extraction instructions) \u2192 map to registry (exact/semantic/composite matching) \u2192 add reference tables \u2192 publish an immutable version.\n\nField features: format constraints (regex validation with empty/flag/constant fallback), modifiers (date/number format, alias mapping, max_length), bypass strategies (constant, generator, reference lookup \u2014 skip LLM), capture submoves (match \u2192 compute \u2192 reason), output name remapping.\n\nVersioning: Live (published, read-only), Workshop (mutable draft), Version History (timeline with diff). Test extraction compares draft vs. live results before publishing.\n\n## Extraction Jobs (Runs)\n\nA job applies a schema to documents, producing a grid (rows = documents, columns = fields). Navigate to Structuring \u2192 Runs \u2192 New.\n\n**4-phase pipeline:**\n1. **Resolve** \u2014 ~30% of cells in seconds. Graph matches, fuzzy name matching, concept-synonym expansion, 3-tier reference lookup (normalize \u2192 fuzzy \u2192 AI), description scan. No AI calls (except rare Haiku fallback). Values normalized: dates \u2192 YYYY/MM/DD, numbers \u2192 2 decimal places.\n2. **Agent** \u2014 AI reviews gap patterns and produces typed strategy per field: compute (formula from grid values), transfer (copy from equivalent field), extract (re-read document with instructions, 5 concurrent), skip (with reasoning). Fields with manual instructions are always extracted, never skipped.\n3. **Validation** \u2014 Cross-field sanity checks: date_sanity, amount_mismatch, lookup_failed, low_confidence_outlier, unexpected_empty. Flags are informational only \u2014 never block output.\n4. **Re-read** \u2014 Context-aware gap filling. For each empty/low-confidence cell, AI re-reads the original document with field instruction + full grid context. Respects the confidence gate: cells \u2265 0.7 confidence are permanently protected.\n\nPer-cell provenance: confidence (0.0\u20131.0), resolution_type (graph_match | agent_derived | source_reread | unresolved), phase (1\u20134), reasoning trace, source reference (document, page, field).\n\n## Cases & Document Linking\n\nRegistry fields can be link keys: Identity (company/person names), Transaction (contract/PO/invoice numbers), Reference (project codes, cost centers). The linking pipeline normalizes values and builds a bipartite graph of documents \u2194 entities.\n\nA **case** = 2+ documents connected through transaction/reference entities. An **entity group** = 2+ documents connected through identity-only entities. High-frequency entities (>30% of documents) are auto-excluded from case formation.\n\nCase detail: documents, shared entities, evidence chain, timeline, AI-generated narration. Document Graph provides a D3-force visual layout. Case templates auto-discovered after 3+ cases form.\n\n## Smart Matching\n\nUpload CSV/Excel as reference datasets. Define field-to-field comparisons with weighted strategies: exact (case-insensitive), fuzzy (token-based with similarity threshold), date_range (configurable tolerance), numeric_range (percentage or absolute tolerance). AI can auto-suggest field mappings.\n\nResults: top 5 candidates per document with confidence scores and per-field evidence breakdown.\n\n## Validation & Quality\n\n- **Validation checks**: Schema-level rules (field format, value range, cross-field consistency, AI-proposed coherence). Run during Phase 3.\n- **Golden samples**: Manually-created reference datasets. Benchmark runs compare extraction vs. golden for per-field accuracy with AI judge verdicts.\n- **Approval gates**: Threshold-based auto-approve/flag (minimum confidence, validation pass rate, field coverage). Failed rows go to manual review queue.\n\n## Delivery\n\nDestinations: Webhook (HMAC-SHA256 signed), REST API (configurable headers), SFTP, Email (attachments), S3/R2 (cloud storage).\n\nField mappings transform output fields to match destination format. Triggers: auto on approval (stage/push), scheduled (cron), or manual. Failed exports retry with exponential backoff.\n\nDialects control serialization: date_format, number_locale, CSV delimiter, null representation, boolean format, encoding (UTF-8, UTF-8-BOM, ISO-8859-1).\n\n## Search & Navigation\n\n**Omnisearch** (Cmd+K / Ctrl+K): searches across documents, extracted values, field names, schema names, and sources simultaneously.\n\nDocument filters: field-value conditions with autocomplete, comparison operators (eq, contains, gt, between, is_empty), combinable. URL-serializable and saveable as presets.\n\nKeyboard shortcuts: Cmd+K (search), Cmd+J (quick extract), Escape (close overlays).\n\n## Team & Settings\n\n4 roles: Viewer (read-only), Member (full CRUD), Admin (+ team management), Owner (+ billing, API keys, org settings). New members auto-match by email domain with pending approval.\n\nUsage & Registry: per-feature cost breakdown, daily cost chart, call log with model/tokens/cost. Admin master view for cross-tenant stats.\n\n## API\n\nBase URL: `https://api.talonic.com`. Auth: `Authorization: Bearer tlnc_...` (SHA-256 hashed, shown once at creation). Scopes: extract, read, write.\n\nKey endpoints:\n- POST /v1/extract \u2014 Synchronous/async document extraction (`include_markdown=true` returns OCR text, `processing_mode=batch` for 50% cost)\n- GET /v1/documents \u2014 List with cursor pagination; GET /v1/documents/:id/markdown for OCR text\n- GET /v1/extractions \u2014 Query results and field corrections\n- POST /v1/schemas \u2014 Create/manage extraction schemas\n- GET /v1/jobs \u2014 Track async jobs and results; N-Shot comparisons, overrides, judge decisions\n- POST /v1/sources \u2014 Manage API sources and document ingest\n- POST /v1/webhooks \u2014 Configure webhook endpoints\n- /v1/resolutions \u2014 Resolution runs: list, create, get, execute, delete, results\n- /v1/linking \u2014 Link keys, document links, entity graph, classify, backfill, document-case map\n- /v1/schema-graph \u2014 Schema classes, versions, diffs (approve/reject), edges, aliases, visualize\n- /v1/structuring \u2014 Validation checks CRUD, approval gates CRUD with rules, result checks, pending approvals, approve/reject, delivery trigger\n- /v1/telemetry \u2014 Per-schema and per-run summaries, trends, field-level breakdowns\n- /v1/validation \u2014 Golden samples (list, get, delete), validation runs (list, create, get, delete, results)\n- /v1/credits \u2014 Balance, history, usage summary, daily usage, per-request usage log\n- /v1/cases \u2014 Status updates, edges, edge confirm/reject, split/merge, completeness, pin/remove documents\n- /v1/batches \u2014 Sync with provider, cancel\n- /v1/matching \u2014 Smart run, AI resolve, strategies CRUD, run results/progress, review\n- /v1/review \u2014 Assign, stats\n- /v1/quality \u2014 Ground truth entries CRUD, benchmark results, benchmark comparison\n- /v1/reference-data \u2014 JSON upload (POST create)\n\nWebhook events: extraction.completed, job.completed, export.completed, validation.completed. All HMAC-SHA256 signed with retry on failure.\n\n## Agent\n\nThe embedded AI assistant accessible from any page. Two modes:\n- **Chat mode** \u2014 Ask questions about the platform, your documents, extraction results, schemas, or workflows. Grounded in platform documentation.\n- **Planning mode** \u2014 Request actions (create schemas, run jobs, configure exports). The agent builds a plan, confirms with you, then executes.\n\nDocument upload flow: Cmd+J or the upload button opens quick extract. Drop a file, select a schema (or let AI discover fields), and get structured results.\n\n## Documentation\n\n- [API Documentation](https://talonic.com/docs): Complete REST API reference\n- [Platform Guide](https://talonic.com/docs/platform): Product documentation and feature guide\n- [OpenAPI Spec](https://talonic.com/docs/openapi.json): Machine-readable API specification\n";
 declare const LLMS_FULL_TXT_HEADER = "# Talonic \u2014 Full Documentation\n\n> This file contains the complete Talonic documentation for LLM consumption.\n> For a summary, see llms.txt.\n\n";
 
-export { API_FAQ, API_NAV_SECTIONS, API_SECTION_META, LLMS_FULL_TXT_HEADER, LLMS_TXT, OPENAPI_SPEC, PLATFORM_FAQ, PLATFORM_NAV_SECTIONS, PLATFORM_SECTION_META, type SectionMeta };
+export { API_FAQ, API_NAV_SECTIONS, API_SECTION_META, LLMS_FULL_TXT_HEADER, LLMS_TXT, MCP_FAQ, MCP_NAV_SECTIONS, MCP_SECTION_META, OPENAPI_SPEC, PLATFORM_FAQ, PLATFORM_NAV_SECTIONS, PLATFORM_SECTION_META, SDK_FAQ, SDK_NAV_SECTIONS, SDK_SECTION_META, type SectionMeta };

package/dist/seo.js

@@ -17149,10 +17149,93 @@ var API_FAQ = [
   { question: "What file formats does the Talonic API support?", answer: "PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, XLSM, PNG, JPG, JPEG, GIF, WEBP, TXT, MD, HTML, XML, JSON, EML, CSV, MSG, BMP, and ZIP archives." },
   { question: "How does authentication work?", answer: "All API requests require a Bearer token in the Authorization header. API keys carry the tlnc_ prefix and are scoped to a source. Create and manage keys from Settings \u2192 API Keys." },
   { question: "What schema formats are supported?", answer: "Three formats: JSON Schema (full control), simplified fields (recommended), and flat key-type maps (quick prototyping). Supported types: string, number, integer, boolean, date, array, object, enum." },
-  { question: "What are the rate limits?", answer: "Free: 50 extractions/day, 5/min burst, 10MB max. Pro: 2,000/day, 30/min, 50MB max. Enterprise: unlimited with custom rates." },
+  { question: "What are the rate limits?", answer: "Per-key rate limits: 100 req/s extraction, 1,000 req/s read, 200 req/s write. Rate-limit headers (X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset) are included on every response." },
   { question: "How do webhooks work?", answer: "Webhooks deliver POST requests with HMAC-SHA256 signed JSON payloads. Events: extraction.complete, extraction.failed, document.ingested. Failed deliveries retry with exponential backoff (1min, 5min, 30min, 4hr)." },
   { question: "Can I extract data asynchronously?", answer: "Yes. Set async: true or provide a webhook_url in the extract request. Returns a 202 with a job ID that you can poll at /v1/jobs/:id." }
 ];
+var SDK_NAV_SECTIONS = [
+  { id: "sdk-overview", label: "Overview", children: [
+    { id: "sdk-introduction", label: "Introduction" },
+    { id: "sdk-installation", label: "Installation" },
+    { id: "sdk-authentication", label: "Authentication" },
+    { id: "sdk-quickstart", label: "Quick Start" }
+  ] },
+  { id: "sdk-client", label: "Client", children: [
+    { id: "sdk-configuration", label: "Configuration" },
+    { id: "sdk-extract", label: "Extract" }
+  ] },
+  { id: "sdk-resources", label: "Resources", children: [
+    { id: "sdk-documents", label: "Documents" },
+    { id: "sdk-extractions", label: "Extractions" },
+    { id: "sdk-schemas", label: "Schemas" },
+    { id: "sdk-jobs", label: "Jobs" }
+  ] },
+  { id: "sdk-cli", label: "CLI", children: [
+    { id: "sdk-cli-usage", label: "Usage" }
+  ] },
+  { id: "sdk-errors", label: "Error Handling", children: [
+    { id: "sdk-error-classes", label: "Error Classes" },
+    { id: "sdk-retries", label: "Retries" }
+  ] }
+];
+var MCP_NAV_SECTIONS = [
+  { id: "mcp-overview", label: "Overview", children: [
+    { id: "mcp-introduction", label: "Introduction" },
+    { id: "mcp-installation", label: "Installation" },
+    { id: "mcp-authentication", label: "Authentication" }
+  ] },
+  { id: "mcp-clients", label: "Client Setup", children: [
+    { id: "mcp-claude-desktop", label: "Claude Desktop" },
+    { id: "mcp-cursor", label: "Cursor" },
+    { id: "mcp-cline", label: "Cline" },
+    { id: "mcp-continue", label: "Continue" },
+    { id: "mcp-cowork", label: "Cowork" }
+  ] },
+  { id: "mcp-tools", label: "Tools", children: [
+    { id: "mcp-talonic-extract", label: "talonic_extract" },
+    { id: "mcp-talonic-search", label: "talonic_search" },
+    { id: "mcp-talonic-filter", label: "talonic_filter" },
+    { id: "mcp-talonic-get-document", label: "talonic_get_document" },
+    { id: "mcp-talonic-to-markdown", label: "talonic_to_markdown" },
+    { id: "mcp-talonic-list-schemas", label: "talonic_list_schemas" },
+    { id: "mcp-talonic-save-schema", label: "talonic_save_schema" }
+  ] },
+  { id: "mcp-resources", label: "Resources", children: [
+    { id: "mcp-schemas-resource", label: "talonic://schemas" }
+  ] },
+  { id: "mcp-advanced", label: "Advanced", children: [
+    { id: "mcp-drag-drop", label: "Drag & Drop in Chat" },
+    { id: "mcp-architecture", label: "Architecture" },
+    { id: "mcp-configuration", label: "Configuration" },
+    { id: "mcp-troubleshooting", label: "Troubleshooting" }
+  ] }
+];
+var SDK_SECTION_META = [
+  { id: "sdk-overview", title: "Node SDK Overview", description: "Install and configure the official Talonic Node.js SDK. Extract structured data from any document with a single function call." },
+  { id: "sdk-client", title: "SDK Client", description: "Configure the Talonic client with API key, base URL, timeout, retries, and custom fetch. Top-level extract method for single-call extraction." },
+  { id: "sdk-resources", title: "SDK Resources", description: "Documents, extractions, schemas, and jobs resource APIs in the Talonic Node SDK." },
+  { id: "sdk-cli", title: "SDK CLI", description: "The talonic CLI binary for command-line extraction, schema management, and document operations." },
+  { id: "sdk-errors", title: "SDK Error Handling", description: "Typed error classes, automatic retries with exponential backoff, and rate limit handling in the Talonic Node SDK." }
+];
+var MCP_SECTION_META = [
+  { id: "mcp-overview", title: "MCP Server Overview", description: "Install the official Talonic MCP server to give AI agents structured document extraction via the Model Context Protocol." },
+  { id: "mcp-clients", title: "MCP Client Setup", description: "Step-by-step setup for Claude Desktop, Cursor, Cline, Continue, and Cowork MCP clients." },
+  { id: "mcp-tools", title: "MCP Tools", description: "Seven MCP tools: extract, search, filter, get document, to markdown, list schemas, and save schema." },
+  { id: "mcp-resources", title: "MCP Resources", description: "The talonic://schemas MCP resource for browsing saved schemas in compatible clients." },
+  { id: "mcp-advanced", title: "MCP Advanced", description: "Drag-and-drop file handling, architecture overview, configuration options, and troubleshooting for the Talonic MCP server." }
+];
+var SDK_FAQ = [
+  { question: "How do I install the Talonic Node SDK?", answer: "Run npm install @talonic/node. Requires Node.js 18 or newer. Zero runtime dependencies." },
+  { question: "How do I extract data from a document with the SDK?", answer: "Call talonic.extract() with a file_path (or file_url/buffer) and a schema defining the fields you want. Returns structured JSON with confidence scores." },
+  { question: "Does the SDK retry on errors?", answer: "Yes. The SDK retries automatically on 429, 500, 502, 503, 504, network errors, and timeouts with exponential backoff capped at 16s. The API can mark errors as non-retryable." },
+  { question: "What error types does the SDK throw?", answer: "TalonicAuthError (401/403), TalonicNotFoundError (404), TalonicValidationError (400/409/413/422), TalonicRateLimitError (429), TalonicServerError (5xx), TalonicNetworkError, and TalonicTimeoutError." }
+];
+var MCP_FAQ = [
+  { question: "What is the Talonic MCP server?", answer: "An official Model Context Protocol server that gives AI agents seven tools for document extraction, search, filtering, and schema management via the Talonic API." },
+  { question: "How do I install the Talonic MCP server?", answer: 'Add a one-line npx invocation to your MCP client config: {"command": "npx", "args": ["-y", "@talonic/mcp@latest"], "env": {"TALONIC_API_KEY": "tlnc_..."}}. No clone or build required.' },
+  { question: "Which MCP clients are supported?", answer: "Claude Desktop, Cursor, Cline, Continue, and Cowork. Any MCP-compliant client can connect." },
+  { question: "How does file upload work in chat clients?", answer: "From v0.1.4, agents can pass file_data (base64) + filename instead of a file path. This handles drag-and-drop in sandboxed chat clients like Claude Desktop." }
+];
 var PLATFORM_FAQ = [
   { question: "What is the Field Registry?", answer: "The unified knowledge graph of all canonical fields discovered across documents. Fields are organized into three tiers based on frequency: Tier 1 (core), Tier 2 (established), Tier 3 (emerging)." },
   { question: "How does the 4-phase extraction pipeline work?", answer: "Phase 1 (Resolve) fills ~30% of cells from graph matches \u2014 no AI needed. Phase 2 (Agent) uses AI strategies. Phase 3 (Validation) runs cross-field checks. Phase 4 (Re-read) fills remaining gaps with targeted document re-reading." },
@@ -17316,8 +17399,14 @@ export {
   API_SECTION_META,
   LLMS_FULL_TXT_HEADER,
   LLMS_TXT,
+  MCP_FAQ,
+  MCP_NAV_SECTIONS,
+  MCP_SECTION_META,
   OPENAPI_SPEC,
   PLATFORM_FAQ,
   PLATFORM_NAV_SECTIONS,
-  PLATFORM_SECTION_META
+  PLATFORM_SECTION_META,
+  SDK_FAQ,
+  SDK_NAV_SECTIONS,
+  SDK_SECTION_META
 };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@talonic/docs",
-  "version": "0.20.2",
+  "version": "0.20.4",
   "description": "Talonic documentation components — API Reference & Platform Guide",
   "license": "UNLICENSED",
   "private": false,