> ## Documentation Index > Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt > Use this file to discover all available pages before exploring further. # Platform Changelog > Track the evolution of Moorcheh platform with detailed release notes, improvements, and updates across versions. ## Moorcheh Platform Changelog Track the evolution of Moorcheh with our detailed changelog, documenting new features, improvements, and updates across versions. ### Security #### Moorcheh Console and core platform backend * **Security update** - Applied security-focused dependency updates and hardening across [console.moorcheh.ai](https://console.moorcheh.ai) and core platform backend services. We recommend rotating API keys if they have not been rotated recently. ### Moorcheh On-Prem 0.1.4 * **Multi-arch Docker** - `moorcheh/server` published as a multi-architecture manifest (`linux/amd64`, `linux/arm64`) for Windows, Linux, Intel Mac, Apple Silicon, and ARM Linux. * **Namespace delete reliability** - `namespaces.delete()` and `moorcheh namespace-delete` wait for the async delete job by default; `--no-wait` restores legacy behavior; server fixes for delete-then-recreate on Windows bind mounts. See [Moorcheh On-Prem changelog — Version 0.1.4](/on-prem/changelog#version-0-1-4) for full release notes. ### Moorcheh On-Prem 0.1.5 * **Community Edition** - Moorcheh On-Prem is now **source-available** on [github.com/moorcheh-ai/moorcheh-on-prem](https://github.com/moorcheh-ai/moorcheh-on-prem). **Free for single-node and non-commercial deployments.** Moorcheh server binary on [Docker Hub](https://hub.docker.com/repository/docker/moorcheh/server/general). * **Contributor docs** - `CONTRIBUTING.md`, refreshed README, and **`test.py`** live integration test for all API endpoints. * **No breaking changes** - `from moorcheh import MoorchehClient` and all CLI commands work as before. See [Moorcheh On-Prem changelog — Version 0.1.5](/on-prem/changelog#version-0-1-5) for full release notes. ### Moorcheh On-Edge 0.2.2 * **Catalog sync (retail kiosk)** - `GET /export` and `export_store()` export catalog text from Moorcheh Edge; voice `POST /catalog/document` chunks and embeds on edge hardware; Admin **Sync from UNO Q** replaces the local SQLite catalog on the display PC. See [Moorcheh On-Edge changelog — Version 0.2.2](/on-edge/changelog#version-0-2-2) for full release notes. ### Moorcheh On-Edge 0.2.3 * **BGE-small embeddings (384-dim)** - Default embedding model switched to `BAAI/bge-small-en-v1.5` for lighter RAM use on **Arduino UNO Q** (\~3.6 GB RAM); default LLM restored to **`qwen2.5:0.5b-instruct`**. * **Breaking change for existing text stores** - dimension changes from **768** to **384**; clear store, remove `~/.moorcheh-edge/models`, and re-upload documents after upgrading. See [Moorcheh On-Edge changelog — Version 0.2.3](/on-edge/changelog#version-0-2-3) for full release notes. ### Improvements #### Answer API * **Source metadata in RAG prompts** - After search, Moorcheh reads the **`source`** field from each chunk's metadata and includes it in the context sent to the AI when generating an answer. This helps the model attribute passages to the right file. No API or response changes for callers. ### Moorcheh On-Prem 0.1.2 * **Multi-provider embeddings** - Choose **Ollama**, **OpenAI**, or **Cohere** for text document and query embeddings via `moorcheh configure` and `~/.moorcheh/config.json`. * **`moorcheh configure`** - Interactive setup for embedding provider, model, and API keys; health and status report `embedding_provider` and `model`. See [Moorcheh On-Prem changelog](/on-prem/changelog) for full release notes. ### Moorcheh On-Prem 0.1.3 * **Path-based file upload** - Async ingest for PDF, DOCX, XLSX, PPTX, TXT, CSV, MD, and JSON from `~/.moorcheh/uploads`; list, get, delete file index, and poll file jobs. * **Fetch text data** - Cursor pagination for text and summary chunks (up to 100 items per page). * **AI Answer (RAG)** - `POST /answer` with Ollama, OpenAI, or Cohere; `moorcheh answer` CLI and `client.answer.generate()`. * **Search** - `namespace` on each result; `#key:value` metadata filters and `#keyword` text filters (cloud parity). See [Moorcheh On-Prem changelog](/on-prem/changelog) for full release notes. ### Moorcheh On-Edge 0.1.1 * **CI and publish pipeline** - Automated PyPI and Docker releases for `moorcheh-edge` and `moorcheh/moorcheh-edge`. * **Multi-arch Docker** - `linux/amd64` and `linux/arm64` images for devices such as Arduino UNO Q. See [Moorcheh On-Edge changelog](/on-edge/changelog) for full release notes. ### Moorcheh On-Edge 0.2.0 * **Flat store with text and vector modes** - Single store per container; client-side BGE embeddings for text; RAG via local Ollama (`POST /answer`, `POST /answer/stream`). * **Voice CLI** - On-device STT (Whisper), TTS (Piper), `voice ask`, and `voice serve` for kiosk hardware. * **Breaking changes** - New upload payload shape, `DELETE /items` and `DELETE /store`; see the On-Edge changelog before upgrading. See [Moorcheh On-Edge changelog](/on-edge/changelog) for full release notes. ### New Features #### Fetch Text Data API * **Cursor pagination** - `GET /documents/fetch-text-data` now returns pages of up to **100** text/summary chunks with `pagination.has_more` and `pagination.next_token` for fetching additional pages. * **Query parameters** - Use `limit` (1–100, default 100) and `next_token` from the previous response to walk through large text namespaces without loading everything at once. See [Fetch Text Data](/api-reference/data/fetch-text-data) in the API reference. ### Python SDK v1.3.7 * **`documents.fetch_text_data` pagination** - Pass `limit` and `next_token` to page through text chunks; response includes `pagination.has_more` and `pagination.next_token` aligned with the API (see [Fetch Text Data (Python SDK)](/python-sdk/data/fetch-text-data)). For full release notes and details, see [moorcheh-python-sdk v1.3.7](https://github.com/moorcheh-ai/moorcheh-python-sdk/releases/tag/v1.3.7). ### Other #### Moorcheh Console * **Paginated chunks view** - The namespace **Chunks** page now supports cursor pagination when browsing stored text chunks, matching the Fetch Text Data API behavior. Open a namespace and go to **Chunks** (e.g. [console.moorcheh.ai/namespaces/…/chunks](https://console.moorcheh.ai/namespaces/moorcheh-docs/chunks)). ### Security #### Backend and dependencies * **Security update** - Applied security-focused dependency updates and hardening across backend services. We recommend upgrading to **moorcheh-sdk** **v1.3.7** and rotating API keys if they have not been rotated recently. ### New Product #### Moorcheh On-Edge * **On-device vector search** - Run fast similarity search locally with the `moorcheh-edge` package and Docker. Upload 1024-dimensional vectors, search on-device, and delete by id - no cloud API keys required. * **Vector-only, lightweight stack** - Binarized vector storage for low-latency search from the `moorcheh-edge` CLI or `MoorchehEdge` Python client on `http://localhost:8080`. See [Moorcheh On-Edge](/on-edge/introduction) for setup, quickstart, and API reference. See [Moorcheh On-Edge changelog](/on-edge/changelog) for full release notes. ### Moorcheh On-Prem 0.1.1 * **`moorcheh-client` v0.1.1** - Patch release for Moorcheh On-Prem with improved reliability, Python 3.10-3.13 support, and expanded client/CLI tests. No breaking changes to the REST API or existing workflows. See [Moorcheh On-Prem changelog](/on-prem/changelog) for full release notes. ### New Product #### Moorcheh On-Prem * **Self-hosted Moorcheh** - Run semantic search and vector storage on your own machine with the `moorcheh-client` package, a Docker-based API server, and Ollama for embeddings - no cloud API keys required. * **Full local stack** - Create text or vector namespaces, upload data, search across namespaces, and manage everything from the `moorcheh` CLI or `MoorchehApiClient` on `http://localhost:8080`. See [Moorcheh On-Prem](/on-prem/introduction) for setup, quickstart, and API reference. ### New Features #### Moorcheh Telegram bot * **Official Telegram assistant** - Search, upload, and manage your Moorcheh knowledge base from Telegram. * **Launch the bot** - Open [@Moorcheh\_official\_bot](https://t.me/Moorcheh_official_bot) and tap **Start** to connect. ### New Features #### List Files API * **New `GET /list-files` endpoint** - List raw file objects in document storage (S3) for a namespace you own: `file_name`, `size` (bytes), and `last_modified` (ISO 8601 from storage). * **Distinct from indexed documents** - This lists **objects under your namespace prefix** in S3. It is not the same as listing indexed text chunks; for pipeline text by ID, use [Get Documents](/api-reference/data/get-documents). See [List Files](/api-reference/files/list-files) in the API reference. ### Python SDK v1.3.6 * **`documents.list_files`** - Call the List Files API from the SDK to enumerate stored file objects for a namespace (see [List Files (Python SDK)](/python-sdk/files/list-files)). For full release notes and details, see [moorcheh-python-sdk v1.3.6](https://github.com/moorcheh-ai/moorcheh-python-sdk/releases/tag/v1.3.6). ### Security #### Backend and dependencies * **Security update** - Applied security-focused dependency updates and hardening across backend services. We recommend upgrading to **moorcheh-sdk** **v1.3.6** and rotating API keys if they have not been rotated recently. ### Breaking changes #### Legacy camelCase removed * **Public API** - Legacy camelCase field names are **no longer accepted** on endpoints that previously documented snake\_case with camelCase aliases (for example the Answer API, upload URL, and delete-file flows). Requests must use **snake\_case** keys only (e.g. `ai_model`, `chat_history`, `file_name`). * **Action required** - If your application still sends camelCase (`aiModel`, `chatHistory`, `fileName`, etc.), update payloads and clients to snake\_case before upgrading. See [API introduction](/api-reference/introduction) and the affected endpoint references. ### API consistency updates #### snake\_case standardization * **Field naming normalization** - Updated request/response documentation and related references to use consistent `snake_case` naming where applicable. * **List Namespaces** - Namespace objects now document `item_count` and `created_at` (snake\_case) instead of `itemCount` and `createdAt`. * **Answer (`POST /answer`)** - Request and response docs use snake\_case (e.g. `ai_model`, `chat_history`, `header_prompt`, `footer_prompt`, `structured_response`; response fields `context_count`, `used_context`, `structured_data`). Legacy camelCase remains accepted until removal (see API reference note). * **Developer clarity** - Examples and parameter docs now align better across API and SDK surfaces. #### Python SDK * **Legacy client unsupported** - The [Legacy Client Methods](/python-sdk/legacy-client) page now states clearly that the old flat client API is **deprecated and no longer supported**; do not use it in new code. Use `MoorchehClient` with `namespaces`, `documents`, `answer`, and related resource methods instead. ### Security #### Backend hardening * **Backend security update** - Applied security and dependency update to all our backend feature. ### AI models & documentation #### Answer API model list * **New models**- Added **Claude Sonnet 4.6**, **Claude Opus 4.6**, **DeepSeek V3.2**, and **Qwen3 Next 80B A3B** to the supported model catalog, with clearer short descriptions for when to use each model. * **Retired from docs**- Removed older catalog entries (Claude Sonnet 4, Sonnet 4.5, Opus 4.5, Llama 3.3 70B) from the public model tables so the docs match what we support today. * **Credits**- **DeepSeek V3.2** is priced at **2 credits** per use (see [Generate AI Answer](/api-reference/ai/generate) and [Python SDK](/python-sdk/ai/generate)). #### Python SDK docs * **Aligned with API reference**- The Python SDK **Generate AI Answer** page uses the same model table and updated examples (`ai_model` defaults and samples). ### Security * **Dependency and security updates**- We applied security-focused updates across almost all of our backend functions that ship with a `package.json` (Node.js services and Lambdas), including dependency refreshes and hardening. We recommend using the latest API keys. ### New Features #### Fetch Text Data API * **New `GET /documents/fetch-text-data` endpoint** - Retrieve text and summary chunks from a text-type namespace via the public API * **List stored chunks** - Use for display, export, or RAG; response includes statistics, metadata, and up to 100 items per request * **Text namespaces only** - Supports namespaces with `type === "text"`; authenticate with `x-api-key` See [Fetch Text Data](/api-reference/data/fetch-text-data) in the API reference. ### Python SDK v1.3.3 * **Direct AI without namespace** - Direct AI mode no longer requires a namespace, simplifying general AI generation workflows * **Structured response parameter** - Define and enforce structured output formats for more reliable integration with downstream applications (see [Structured output](/api-reference/ai/generate#structured-output)) * **Improved validation and tests** - Better input validation and test coverage for AI generation requests For full release notes and details, see [moorcheh-python-sdk v1.3.3](https://github.com/moorcheh-ai/moorcheh-python-sdk/releases/tag/v1.3.3). ### Other #### Moorcheh Console * **Security updates** - Security improvements applied to the Moorcheh Console. * **View data items in namespaces** - The console shows up to 100 data items from your namespace. Open a namespace to see its contents at [console.moorcheh.ai/namespaces](https://console.moorcheh.ai/namespaces/). ### New Features #### Pre-signed Upload URL for Large Files * **New `/upload-url` endpoint** - Get a pre-signed S3 URL to upload files directly, bypassing the 10MB API Gateway limit * **Upload files up to 5GB** - Support for large file uploads directly to S3 * **Automatic processing** - Files uploaded via pre-signed URL are automatically processed through the document pipeline **Benefit:** Upload large documents (up to 5GB) without API Gateway size restrictions. The two-step process (get URL, then upload to S3) ensures reliable handling of large files. See [Get Upload URL](/api-reference/files/upload-file-url) in the API reference. #### Delete File * **New `/delete-file` endpoint** - Delete one or more files from a namespace in document storage (S3) * **Single or multiple files** - Use `fileName`, `fileNames`, or query `fileName`; all listed files are deleted in one request * **Per-file results** - Response includes status per file (`deleted` or `error`) See [Delete File](/api-reference/files/delete-file) in the API reference. ### Removed #### Upload File API documentation * **Upload File endpoint docs removed** - The standalone Upload File (`/upload-file`) API reference page has been removed. Use [Get Upload URL](/api-reference/files/upload-file-url) for file uploads (supports up to 5GB). ### New Features #### Answer Endpoint: Structured Output * **Structured output in response** - The answer endpoint now returns structured output for easier parsing and integration with downstream systems * **Predictable response schema** - Consistent JSON structure for answers, citations, and metadata See [Structured Output](/api-reference/ai/generate#structured-output) in the Generate AI Answer API reference. #### Enterprise Package & Licensing * **Enterprise customer package** - New package tailored for enterprise customers with advanced features and support * **Terraform-based licensing** - Licensing and provisioning for enterprise deployments managed via Terraform for reproducible, infrastructure-as-code workflows **Benefit:** Integrate answer responses directly into your applications with a well-defined structure. Enterprise teams can provision and manage Moorcheh with Terraform while enforcing licensing through infrastructure. ### Security & Improvements #### Answer Endpoint * **Max token security** - Updated security controls for maximum tokens on the answer endpoint to prevent abuse and ensure resource fairness #### Integrations * **n8n: AI models in npm registry** - Updated AI models available in the n8n npm registry for the Moorcheh node * **moorcheh-mcp: Security and version** - Security improvements and version update for the Moorcheh MCP server * **Chat boilerplate: GitHub repo initialization** - Chat boilerplate now also initializes a GitHub repository when you create a new project ### New Features #### Python SDK Updates * **Async client support** - New AsyncMoorchehClient for asynchronous operations with FastAPI, aiohttp, and other async frameworks * **Automatic batching** - Automatic batching for document and vector uploads (100 documents per batch) * **File upload method** - Upload files directly via `upload_file()` method supporting PDF, DOCX, XLSX, JSON, TXT, CSV, and Markdown files (10MB max) #### Console: Playground Summaries & Memory Management * **Persistent chat memory** - Each chat conversation maintains its own memory context * **Long conversation support** - Moorcheh internally manages memory to maintain full conversation context * **Maximum output tokens** - Increased output limit to maximum for comprehensive responses * **Namespace locking per chat** - Each conversation locks to its namespace to ensure relevant context without mixing * **Improved document summaries** - Enhanced summaries with full document context for better understanding **Benefit:** Have natural, long-running conversations with full context awareness. Each chat maintains its own memory, and document summaries provide quick context without reading entire documents. ### Improvements #### Console: Context Management * **Isolated conversation memory** - Each chat session maintains separate memory to prevent context mixing * **Full conversation understanding** - Moorcheh ensures the entire conversation meaning is preserved ### Improvements #### Larger File Uploads in Console * **100 MB upload limit** - Upload files up to 100 MB directly from the console * **Flexible formats** - Works with PDF, DOCX, XLSX, JSON, TXT, CSV, and Markdown files * **Automatic ingestion** - Files are queued for processing and indexing once uploaded * **Improved upload status** - Clearer progress and completion states for large files * **Higher AI output** - Generative answers now support up to **8,000 output tokens** for richer responses **Benefit:** Bring richer source material into your namespaces without splitting files. Uploading through the console now supports larger documents so you can ingest comprehensive reports and datasets in one step. #### Usage Notes * Upload time depends on network speed; keep the tab open until the upload completes * Very large documents may take longer to ingest and index after upload * Upload status now reflects chunked progress for large files ### UI & Security Updates * **Accessible console icons** - Refreshed icon set with better contrast and clarity * **Framework security patches** - Updated Next.js and React across `moorcheh.ai`, `console.moorcheh.ai`, and the chat boilerplate to include the latest security fixes ### New Features #### Upload Files via Public API * **Direct file upload** - Upload files directly to your namespace using the public API endpoint * **Multiple file formats supported** - PDF, DOCX, XLSX, JSON, TXT, CSV, and Markdown files * **Multipart form data** - Simple file upload using standard multipart/form-data encoding * **Automatic processing** - Files are automatically queued for ingestion and indexing **Benefit:** Programmatically upload documents to your namespaces without using the console. Perfect for automation, CI/CD pipelines, and bulk document ingestion workflows. #### Supported File Types | Extension | Description | | --------- | ---------------------------- | | `.pdf` | PDF documents | | `.docx` | Microsoft Word documents | | `.xlsx` | Microsoft Excel spreadsheets | | `.json` | JSON files | | `.txt` | Plain text files | | `.csv` | CSV files | | `.md` | Markdown files | #### Quick Start Example ```bash cURL theme={null} curl -X POST "https://api.moorcheh.ai/v1/namespaces/{namespace-name}/upload-file" \ -H "x-api-key: YOUR_API_KEY" \ -F "file=@path/to/your/document.pdf" ``` ### Important Notes #### Processing Time After uploading a file, it will be queued for ingestion. The file needs to be processed and indexed before it becomes searchable. To verify ingestion status, use the **List Namespaces** endpoint and check the `total_items` count before and after upload. #### File Size Limit Maximum file size is **10MB** per upload. For larger files, consider splitting them into smaller documents or using the Upload Text Data endpoint for preprocessed content. #### Text Namespace Required File uploads are only supported for **text-type namespaces**. Vector namespaces cannot accept file uploads directly. ### New Features #### Document Summaries * **Automatic summary generation** - Uploaded documents now include automatic summaries * **Summaries in search results** - Summaries appear in search results to provide context * **Batch summary generation** - One summary is generated for every 100 chunks of content **Benefit:** Get quick context about documents without reading the full content. Summaries help you understand document relevance at a glance. #### Upload Text Directly from Console * **No file needed** - Paste or type your text content directly in the namespace console * **Faster processing** - Text-only uploads are processed more quickly than file uploads * **Automatic chunking and indexing** - Text is automatically chunked and indexed for search * **Optional metadata** - Add custom metadata fields to organize your content **Benefit:** Quickly add text content without creating files. Perfect for notes, snippets, or content that doesn't need to be stored as a document file. ### Improvements #### Enhanced Search Results * **Summary metadata in results** - Top results may include `summary_text` and `summary_chunk_id` in metadata for better context * **Automatic summary fetching** - Summary information is fetched automatically when available **Example Search Result with Summary:** ```json theme={null} { "id": "doc-123", "score": 0.856432, "label": "Close Match", "text": "...", "metadata": { "title": "Introduction to ML", "summary_text": "This document provides an overview of machine learning...", "summary_chunk_id": "summary-123" } } ``` ### Performance Improvements #### Faster Search Performance * **10x faster search queries** - Experience dramatically improved search speeds * **Query time reduced from 5-10s to 1s-2s** for large datasets (100K+ vectors) ### New Features #### Chat History Management for console only * Automatic conversation tracking for all AI interactions * Auto-generated conversation titles (first 30 characters) #### AI Reasoning Transparency * See how AI models think through problems in real-time * Reasoning process separated from final answer * Streaming support for live thought process display * Works with DeepSeek R1 and OpenAI o1 models **Benefit:** Understand AI decision-making and build trust in AI-generated responses ### AI Model Updates #### New Models Added * **Claude Sonnet 4.5** - Latest Anthropic model with enhanced capabilities * **OpenAI GPT OSS 120B** - Large-scale model with hybrid reasoning * **Qwen 3 32B** - Advanced multilingual model #### Models Removed * Claude 3.7 Sonnet - Will be deprecated by provider in 2026 **Total Models:** 8 AI models available from Anthropic, Meta, Amazon, DeepSeek, OpenAI, and Qwen ### Security #### Patches * Applied security patches across dependencies * General hardening and minor fixes ### Dependencies #### Updates * Updated project dependencies to latest compatible versions ### Search Scoring #### ITS Score Display * Display of ITS (Information Theoretic Similarity) scores now uses a square-root transformation for improved readability * Backend label mapping updated; API responses now return the new ITS labels ### Direct AI Mode #### Empty Namespace Support * New **Direct AI Mode** when passing empty string `""` as namespace * Direct AI model calls without searching your data for general-purpose AI interactions * Perfect for general AI assistance, creative writing, coding help, and educational content * Maintains all AI model capabilities while bypassing data search functionality #### API Flexibility * Two distinct modes: **Search Mode** (with namespace) and **Direct AI Mode** (empty namespace) * Search Mode: Full data search and retrieval capabilities * Direct AI Mode: Pure AI model interaction without data constraints * Seamless switching between modes based on namespace parameter ### Enhanced Error Handling #### Field Validation * Specific error messages for field validation based on namespace mode * Empty namespace with invalid fields: `"Bad Request: namespace, query, temperature, chatHistory, footerPrompt, headerPrompt, aiModel are the only allowed fields with empty namespace."` * Provided namespace with invalid fields: `"Bad Request: namespace, query, top_k, threshold, type, kiosk_mode, aiModel, chatHistory, headerPrompt, footerPrompt, temperature are the only allowed fields with provided namespace."` * Improved developer experience with clear guidance on correct field usage Security update. ### Advanced Search Filters #### Metadata Filters * New `#key:value` filter syntax for document properties * Filter by category, priority, author, status, and other metadata fields * Case-insensitive exact matching with automatic key validation * Unknown metadata keys are gracefully ignored without errors #### Keyword Filters * New `#keyword` filter syntax for text content * Search within document text for specific keywords like #important, #urgent, #critical * Multiple keyword filters require ALL keywords to be present * Case-insensitive matching within actual document content #### Combined Filtering * Combine semantic search with metadata and keyword filters * Format: `search_text #key:value #keyword` * Filters must be placed at the END of query string * Use hyphens instead of spaces in filter values #### Enhanced Search API * Updated Search API documentation with comprehensive filter examples * New timing fields: `earlyFilter` and `applyMetadataFilter` * Improved search optimization with early filtering capabilities * Enhanced response structure for better performance tracking ### Vector Metadata Enhancement #### Flexible Metadata Structure * Any fields beyond `id` and `vector` are automatically treated as metadata * Enhanced vector upload with automatic metadata extraction * Support for custom fields like category, source, product\_id, customer\_id * Metadata is searchable and filterable in vector operations #### Updated Vector Upload API * Simplified request structure with automatic metadata handling * Enhanced examples showing metadata usage in vector uploads * Improved documentation for vector metadata best practices * Better error handling for metadata validation ### Documentation Updates #### Search API Documentation * Comprehensive filter usage examples with cURL requests * Updated response structure documentation * New timing information for performance monitoring * Enhanced API call examples for different filter combinations #### Vector Upload Documentation * Updated examples showing metadata fields in vector uploads * Clear explanation of automatic metadata handling * Enhanced request parameter documentation * Improved error handling and validation examples ### Technical Improvements #### Performance Enhancements * Early filtering optimization for better search performance * Enhanced timing tracking for debugging and optimization * Improved search result relevance with metadata filtering * Better resource utilization in vector operations #### Developer Experience * Simplified filter syntax for easier implementation * Comprehensive examples for all filter combinations * Better error messages and validation feedback * Enhanced API documentation with practical use cases ### Document Retrieval #### Get Documents by ID * New endpoint to retrieve specific documents from text-based namespaces * Endpoint: POST /namespaces/{namespace}/documents/get * Request Format: Send array of document IDs in request body * Flexible Access: Retrieve up to 100 documents in a single API call ### Local Development #### Local MCP Support * Run Moorcheh's Model Context Protocol locally for development and testing * Offline Development: Test and develop integrations without internet connectivity * Local Environment: Full feature parity with cloud environment for testing ### Document Upload System #### Features * Console Upload Interface: Direct document upload through the web console * Supported File Formats: PDF, DOCX, CSV, JSON, TXT, MD, Excel files * Real-time Status Tracking: Live document processing status displayed in namespace view ### Enhanced AI Models #### New Models * Claude Sonnet 4 Support: Added new AI model option for improved performance ### Namespace Improvements #### New Features * Document Status Display: View processing status of uploaded documents * Upload Progress Tracking: Monitor document processing in real-time * File Management: Better organization and tracking of uploaded content ### Dashboard #### Overview * Quick overview tab for overall usage * Weekly API usage line graph * Quick usage metrics * Recent activity feed #### Usage Analytics * Weekly usage graphs for specific APIs * Platform health dashboard * Usage limit visualizations with bar graphs * Daily cost analysis (weekly view) with bar graphs #### Performance Monitoring * Quick performance cards * 24-hour performance matrix with line graphs * Average execution time tracking for upload, search, and answer operations ### Namespace Management #### Text Namespaces * Namespace name and item count * Creation time tracking #### Vector Namespaces * Namespace name and vector dimensions * Item count and creation time tracking ### Playground #### Chat Interface * Kiosk mode for focused interactions * AI model selection #### Settings & Configuration * Header and footer prompt customization * Model parameters (model selection, temperature) * Top-k and threshold controls * Metadata toggle options * JSON configuration export #### Chat History * Conversation titles and content * Chat timing and timestamps * Local storage persistence ### API Key Management #### Key Operations * Create new API keys * Revoke existing keys * Delete API keys ### Pricing Plans #### Subscription Tiers * Community plan * Professional plan * Pay-as-you-go options * Enterprise solutions ### Documentation #### Developer Resources * Complete API reference * Python SDK documentation