Graphlit Changelog
DocumentationDeveloper PortalMore Information
  • 🐰May 2025
    • May 11: Support for Amazon Bedrock models, McPoogle MCP search engine, bug fixes
  • 🐰April 2025
    • April 26: Support for OpenAI image generation, GPT-4.1, o3 and o4-mini models, bug fixes
    • April 13: Support for memory, email thread collections, Groq Llama 4 models, bug fixes
  • 🍀March 2025
    • March 27: Support for Twitter/X feed, Gemini 2.5 Pro model
    • March 15: Support for Podscan search, image similarity search, 'exists' and 'upsert' mutations
    • March 13: Support for classification workflow, notifications, Cohere Command A model, bug fixes
    • March 6: Support for MCP Server, Mistral OCR, retrieveSources, GPT-4.5, Sonnet 3.7, bug fixes
  • 💌February 2025
    • February 16: Support for Trello feed, Assembly.AI audio transcription, OpenAI o3-mini, bug fixes
  • 🎆January 2025
    • January 30: Support for Uppy file uploader, Deepseek Reasoner model, bug fixes
    • January 19: Support for at-cost LLM token pricing, multi-tenant feed deletion, bug fixes
    • January 10: Support for conversation message images, email filtering, Diffbot API key, bug fixes
    • January 4: Support for askGraphlit mutation, storage policies, bug fixes
  • 🎄December 2024
    • December 27: Support for LLM fallbacks, native Google Docs formats, website unblocking, bug fixes
    • December 22: Support for Dropbox, Box, Intercom and Zendesk feeds, OpenAI o1, Gemini 2.0, bug fixes
    • December 9: Support for website mapping, web page screenshots, Groq Llama 3.3 model, bug fixes
    • December 1: Support for retrieval-only RAG pipeline, bug fixes
  • 🦃November 2024
    • November 24: Support for direct LLM prompt, multi-turn image analysis, bug fixes
    • November 16: Support for image description, multi-turn text summarization
    • November 10: Support for web search, multi-turn content summarization, Deepgram language detection
    • November 4: Support for Anthropic Claude 3.5 Haiku, bug fixes
  • 🎃October 2024
    • October 31: Support for simulated tool calling, bug fixes
    • October 22: Support for latest Anthropic Sonnet 3.5 model, Cohere image embeddings
    • October 21: Support OpenAI, Cohere, Jina, Mistral, Voyage and Google AI embedding models
    • October 9: Support for GitHub repository feeds, bug fixes
    • October 7: Support for Anthropic and Gemini tool calling
    • October 3: Support tool calling, ingestBatch mutation, Gemini Flash 1.5 8b, bug fixes
  • 🎒September 2024
    • September 30: Support for Azure AI Inference models, Mistral Pixtral and latest Google Gemini models
    • September 26: Support for Google AI and Cerebras models, and latest Groq models
    • September 3: Support for web search feeds, model deprecations
    • September 1: Support for FHIR enrichment, latest Cohere models, bug fixes
  • 🎂August 2024
    • August 20: Support for medical entities, Anthropic prompt caching, bug fixes
    • August 11: Support for Azure AI Document Intelligence by default, language-aware summaries
    • August 8: Support for LLM-based document extraction, .NET SDK, bug fixes
  • ☀️July 2024
    • July 28: Support for indexing workflow stage, Azure AI language detection, bug fixes
    • July 25: Support for Mistral Large 2 & Nemo, Groq Llama 3.1 models, bug fixes
    • July 19: Support for OpenAI GPT-4o Mini, BYO-key for Azure AI, similarity by summary, bug fixes
    • July 4: Support for webhook Alerts, keywords summarization, Deepseek 128k context window, bug fixes
  • 🎓June 2024
    • June 21: Support for the Claude 3.5 Sonnet model, knowledge graph semantic search, and bug fixes
    • June 9: Support for Deepseek models, JSON-LD webpage parsing, performance improvements and bug fixes
  • 💐May 2024
    • May 15: Support for GraphRAG, OpenAI GPT-4o model, performance improvements and bug fixes
    • May 5: Support for Jina and Pongo rerankers, Microsoft Teams feed, new YouTube downloader, bug fixes
  • 🐇April 2024
    • April 23: Support for Python and TypeScript SDKs, latest OpenAI, Cohere & Groq models, bug fixes
    • April 7: Support for Discord feeds, Cohere reranking, section-aware chunking and retrieval
  • 🍀March 2024
    • March 23: Support for Linear, GitHub Issues and Jira issue feeds, ingest files via Web feed sitemap
    • March 13: Support for Claude 3 Haiku model, direct ingestion of Base64 encoded files
    • March 10: Support for Claude 3, Mistral and Groq models, usage/credits telemetry, bug fixes
  • 🌧️February 2024
    • February 21: Support for OneDrive and Google Drive feeds, extract images from PDFs, bug fixes
    • February 2: Support for Semantic Alerts, OpenAI 0125 models, performance enhancements, bug fixes
  • 🎆January 2024
    • January 22: Support for Google and Microsoft email feeds, reingest content in-place, bug fixes
    • January 18: Support for content publishing, LLM tools, CLIP image embeddings, bug fixes
  • 🎄December 2023
    • December 10: Support for OpenAI GPT-4 Turbo, Llama 2 and Mistral models; query by example, bug fixes
  • 🎃October 2023
    • October 30: Optimized conversation responses; added observable aliases; bug fixes
    • October 15: Support for Anthropic Claude models, Slack feeds and entity enrichment
  • 🛠️September 2023
    • September 24: Support for YouTube feeds; added documentation; bug fixes
    • September 20: Paid subscription plans; support for custom observed entities & Azure OpenAI GPT-4
    • September 4: Workflow configuration; support for Notion feeds; document OCR
  • 🎂August 2023
    • August 17: Prepare for usage-based billing; append SAS tokens to URIs
    • August 9: Support direct text, Markdown and HTML ingestion; new Specification LLM strategy
    • August 3: New data model for Observations, new Category entity
  • 🎇July 2023
    • July 15: Support for SharePoint feeds, new Conversation features
  • Graphlit Platform
    • Data API Changelog
Powered by GitBook
On this page
  • New Features
  • Bugs Fixed
  1. January 2024

January 18: Support for content publishing, LLM tools, CLIP image embeddings, bug fixes

PreviousJanuary 22: Support for Google and Microsoft email feeds, reingest content in-place, bug fixesNextDecember 10: Support for OpenAI GPT-4 Turbo, Llama 2 and Mistral models; query by example, bug fixes

Last updated 1 year ago

New Features

  • Graphlit now supports content publishing, where documents, audio transcripts and even image descriptions, can be summarized, and repurposed into blog posts, emails or AI-generated podcasts. With the new publishContents mutation, you can configure LLM prompts for summarization and publishing, and assign specifications to use different models and/or system prompts for each step in the process. The published content will be reingested into Graphlit, and can be searched or used for conversations, like any other form of content.

  • Graphlit now supports publishing conversations as content with the new publishConversation mutation. You can generate text or audio transcripts of your conversations, to be reused in other tools.

  • Graphlit now supports bulk summarization of contents with the summarizeContents mutation. You can filter a set of content, by feed, by observable or by similar text, and run a set of summarizations across each content in parallel.

  • Graphlit now supports LLM entity extraction, with the new MODEL_TEXT entity extraction service type. Similar to using Azure Cognitive Service Text Analytics, you can use any OpenAI or Anthropic model for extracting entities from text. Internally the LLM returns JSON-LD entities, which we convert into Person, Organization, Place, etc. entities and assign observations to the extracted content.

  • Graphlit now supports LLM tools (aka function calls) with OpenAI models. You can define the tools to be used with the LLM in the specification object. With the new extractContents mutation, you can execute a prompt against content using a specification with tools defined. The mutation will return the JSON arguments assigned by the LLM.

  • Graphlit now supports callback webhooks for LLM tools. If you assign a URI in the ToolDefinition object, Graphlit will call your webhook the tool name and JSON arguments. When you respond to the webhook with JSON, we will add that response to the LLM messages, and ask the LLM to complete the original prompt.

  • Graphlit now supports the selection of the with the preparation workflow. Also, you can assign your own Deepgram API key, which will be used for audio transcription using that workflow.

  • Added support for CLIP image embeddings using , which can be used for similar image search. If you search for contents by similar contents, we will now use the content's text and/or image embeddings to find similar content.

  • Added support for dynamic web page ingestion. Graphlit now navigates to and automatically scrolls web pages using , so we capture the fully rendered HTML before extracting text. Also, we now support web page screenshots, if enabled with enableImageAnalysis property in preparation workflow. These screenshots can be analyzed with multimodal modals, such as GPT-4 Vision, or can be used to create image embeddings for similar image search.

  • Added table parsing when preparing documents. We now store structured (tab-delimited) text in the JSON text mezzanine which is extracted from documents in the preparation workflow.

  • Added reverse geocoding of lat/long locations found in image or other content metadata. We now store the real-world address with the content metadata, for use in conversations.

  • Added assistant messages to the conversation message history provided to the LLM. Originally we had included only user messages, but now we are formatting both user and assistant messages into the LLM prompt for conversations.

  • Added new chunking algorithm for text embeddings. We support semantic chunking at the page or transcript segment level, and now will create embeddings from smaller sized text chunks per page or segment.

  • Added content metadata to text and image embeddings. To provide better context for the text embeddings, we now include formatted content metadata, which includes fields like title, subject, author, or description. For emails, we include to, from, cc, and bcc fields.

  • Added helper mutations isContentDone and isFeedDone which can be used for polling completion of ingested content, or all content ingested by a feed.

  • Added richer image descriptions generated by the GPT-4 Vision model. Now these provide more useful detail.

  • Added validation of extracted hyperlinks. Now we test the URIs and remove any inaccessible links during content enrichment.

  • Added deleteContents, deleteFeeds, and deleteConversations mutations for multi-deletion of contents, feeds or conversations.

  • Added deleteAllContents, deleteAllFeeds, and deleteAllConversations mutations for bulk, filtered deletion of entities. You can delete all your contents, feeds, or conversations in your project, or a filtered subset of those entities.

  • Starter tier now has a higher content limit of 100K content items.

  • In the OpenAIImageExtractionProperties type, the detailMode field was renamed to detailLevel.

  • Each SummarizationStrategy object now accepts the specification which is used by the summarization, rather than being assigned at the preparation workflow stage.

  • addCollectionContents and removeCollectionContents mutations have been deprecated in favor of addContentsToCollections and removeContentsFromCollection mutations.

Bugs Fixed

  • GPLA-1846: Parse Markdown headings into mezzanine JSON

  • GPLA-1779: Not returning SAS token with mezzanine, master URIs

  • GPLA-1348: Summarize text content, not just file content

  • GPLA-1297: Not assigning content error message on preparation workflow failure

🎆
💡
💡
💡
💡
💡
💡
💡
ℹ️
⚡
⚡
⚡
Deepgram model (such as Meeting, Phonecall or Finance)
Roboflow
Browserless.io