# Cortex SDK ## Docs - [Add User Memory](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/add-memories.md): Store new user memories for future reference. - [Create Embeddings Tenant](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/create-embeddings-tenant.md) - [Create Tenant](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/create-tenant.md): Create a tenant for your account. - [Delete User Memory](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/delete-memory.md): Permanently remove a specific user memory from storage. - [Delete Embeddings](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/delete-raw-embeddings.md): Delete embedding chunks by chunk ID. - [Delete Sources](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/delete-sources.md) - [Fetch Content](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/fetch-source-content.md): Fetch the content of a source ingested. - [Filter Raw Embeddings](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/filter-raw-embeddings.md): Retrieve embeddings for specific chunk IDs. Use this when you already know the chunk IDs and need their corresponding embeddings. - [Full Text Search](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/full-text-search.md): Perform full text search for exact matches within your indexed sources or memories. Choose between 'OR' and 'AND' operators to control how search terms are combined for precise text matching. Use `search_mode` to specify what to search: - "sources" (default): Search over indexed… - [Graph Relations By Source Id](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/graph-relations.md): Retrieve relations for a specific source. - [Hybrid Search](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/hybrid-search.md): Search for relevant content within your indexed sources or user memories. Results are ranked by relevance and can be customized with parameters like result limits, alpha weighting, and recency preferences. Use `search_mode` to specify what to search: - "sources" (default):… - [Upload Embeddings](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/insert-raw-embeddings.md): Upload pre-computed embeddings for advanced similarity search. - [List Sources](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/list-sources.md): Retrieve all sources for a specific tenant and subtenant combination. - [List Sources By ID](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/list-sources-by-id.md): Retrieve specific sources by their IDs. - [QnA](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/qna.md): Ask a question and get an AI-generated answer based on your indexed sources or memories. - [Search Embeddings](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/search-raw-embeddings.md): Find similar chunks using an embedding vector. - [Get Tenant Stats](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/tenant-stats.md): Retrieve usage stats for your tenant. - [Upload App Sources](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/upload-app.md): Specifically built to handle knowledge from workplace apps. Parsing, chunking, and indexing depends on the kind of app (eg - gmail, slack, documents, etc). - [Upload Content](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/upload-content.md): Upload raw text or markdown content for ingestion. Supports both single and batch uploads via the contents list in the request. - [Upload Document](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/upload-document.md): Upload one or more documents for ingestion. Supports both single and batch uploads. For single file: send one file with the 'files' field. For batch: send multiple files with the 'files' field (FastAPI will parse as list). - [Verify Processing](https://cortex-ad5578da.mintlify.app/api-reference/endpoint/verify-processing.md): Check the current processing status of your uploaded content. - [Error Responses](https://cortex-ad5578da.mintlify.app/api-reference/error-responses.md): Comprehensive guide to HTTP error responses and their meanings across all Cortex API endpoints - [Introduction](https://cortex-ad5578da.mintlify.app/api-reference/introduction.md): You can generate and manage API keys from your Cortex Dashboard. All endpoints require an API key sent as a Bearer token in the Authorization header. - [SDKs - Node and Python](https://cortex-ad5578da.mintlify.app/api-reference/sdks.md): Official TypeScript/Node.js and Python SDKs so that you can integrate Cortex AI into your application with ease. - [Changelog](https://cortex-ad5578da.mintlify.app/changelog.md): Stay up to date with the latest features, improvements, and updates to Cortex. We're constantly improving our platform to deliver better performance, new features, and enhanced developer experience. - [Core Concepts](https://cortex-ad5578da.mintlify.app/concepts.md): Understand the core concepts of using Cortex - [AI Memories](https://cortex-ad5578da.mintlify.app/essentials/ai-memories.md): Store, retrieve, and personalize user experiences with dynamic AI memories that evolve over time, enabling your app to remember preferences, context, and past interactions for smarter, more adaptive responses. - [Responses](https://cortex-ad5578da.mintlify.app/essentials/answers.md): Cortex generates smart, grounded, and personalized responses to every user query. This page explains how response generation works, how it adapts over time, and the advanced capabilities built into the system. - [Bring your own data from any app](https://cortex-ad5578da.mintlify.app/essentials/app-integration.md): Learn how to ingest information from Google Drive, Slack, Notion, and other apps using Composio and store it in Cortex - [Customization](https://cortex-ad5578da.mintlify.app/essentials/customisation.md): Let your users define how they want the AI to respond with preferences for format, tone, depth, and structure to create truly personalized experiences. - [Supported File Formats](https://cortex-ad5578da.mintlify.app/essentials/file-formats.md): Comprehensive list of all supported file formats for document processing in Cortex - [Knowledge Graphs](https://cortex-ad5578da.mintlify.app/essentials/graph-rag.md): Automatically extract and leverage entity relationships from your data to provide richer context and deeper insights in every search and answer. - [Metadata](https://cortex-ad5578da.mintlify.app/essentials/metadata.md): Add structured metadata to your documents for precise filtering and targeted queries, supercharging your search experience with file type, owner, and custom (upto 15) fields. - [Multi-Step Retrievals](https://cortex-ad5578da.mintlify.app/essentials/multi-step.md): Cortex automatically handles very complex questions using an in-built reasoning engine that runs multiple parallel searches, figures out the best sequence, and returns complete answers for sophisticated workflows. - [Multi-Tenant Support](https://cortex-ad5578da.mintlify.app/essentials/multi-tenant.md): Create completely isolated workspaces called tenants for secure, scalable B2B platforms that serve many organizations without cross-contamination of data. - [Retrievals](https://cortex-ad5578da.mintlify.app/essentials/retrievals.md): Fine-tune your AI retrievals with complete control over parameters like recency bias and search alpha to get more accurate, relevant, and high-quality results. - [Self-Improving Personalization](https://cortex-ad5578da.mintlify.app/essentials/self-improving.md): Cortex includes memory that improves over time, learning user preferences for formats, content types, and question styles to create personalized, habit-forming experiences. - [Web Search](https://cortex-ad5578da.mintlify.app/essentials/web-search.md): Cortex can search the internet for real-time information when your data doesn't contain the answer, keeping your AI relevant with current events, regulations, and trends. - [Introduction](https://cortex-ad5578da.mintlify.app/index.md): The retrieval layer with built-in memory. See how Cortex personalises your LLM apps, delivers exceptional results, and delights your users with a great experience. - [Quickstart](https://cortex-ad5578da.mintlify.app/quickstart.md): Start building amazing LLM experiences in under 5 minutes - [Building an AI Chief of Staff with Cortex - n8n with NLP](https://cortex-ad5578da.mintlify.app/use-cases/ai-chief-of-staff.md): Guide to creating an autonomous AI that orchestrates actions across all workplace applications using Cortex's function-calling capabilities. - [Build an AI LinkedIn: People search in Natural Language](https://cortex-ad5578da.mintlify.app/use-cases/ai-linkedin-recruiter.md): Learn how to build an intelligent recruiting platform that understands natural language queries like 'find me someone who has 5+ years of experience in machine learning and has worked at Apple before' using Cortex's AI search capabilities. - [Building an AI Travel Planner with Cortex](https://cortex-ad5578da.mintlify.app/use-cases/ai-travel-planner.md): Learn how to build an intelligent travel planning platform that understands natural language queries and provides personalized recommendations using Cortex's AI search and memory capabilities. - [Building Your Own Glean with Cortex](https://cortex-ad5578da.mintlify.app/use-cases/glean-clone.md): Learn how to build a comprehensive workplace search and AI assistant platform using Cortex APIs. This guide covers data ingestion, search capabilities, and AI-powered Q&A across multiple data sources. ## OpenAPI Specs - [openapi](https://cortex-ad5578da.mintlify.app/api-reference/openapi.json) - [delete-sub_tenant](https://cortex-ad5578da.mintlify.app/api-reference/api_schema/delete-sub_tenant.yaml) - [tenant-create_embeddings_tenant](https://cortex-ad5578da.mintlify.app/api-reference/api_schema/tenant-create_embeddings_tenant.yaml)