Hi there, Llama Enthusiasts! 🦙
Welcome to this week's edition of the LlamaIndex newsletter! We're excited to bring you updates including day-zero support for OpenAI's new gpt-5 and gpt-oss models as well as Anthropic's Claude Opus 4.1. Check out these developments along with our comprehensive guides and tutorials to maximize your use of these cutting-edge features.
If you haven't explored LlamaCloud yet, make sure to sign up and get in touch with us to discuss your specific enterprise use case.
🤩 The Highlights:
- OpenAI's First Open-Source LLM Since GPT-2:
gpt-oss-120b&gpt-oss-20bare here with reasoning that matches o4-mini, Apache 2.0 license, and ready to use with LlamaIndex workflows and Ollama. Cookbook. - Multimodal Report Generation: Turn dense PDFs into full multimodal reports with interleaving text and images using LlamaParse's high-res OCR and intelligent document retrieval. LlamaParse, Video Walkthrough.
- Automated Invoice Processing: Build intelligent document agents that extract, validate, and process invoice data with minimal human intervention using LlamaExtract and LlamaParse: Guide.
🗺️ LlamaCloud And LlamaParse:
- 11x AI Case Study: How 11x AI built Alice, the AI SDR, using LlamaParse's multi-modal document ingestion to shrink SDR onboarding time to days. Case Study, Technical Deep Dive.
- Enhanced PDF Retrieval: Improve retrieval accuracy by reranking your LlamaParse PDF results with ZeroEntropy AI rerankers for better semantic search and answer quality. Tutorial.
- Enterprise Document Processing: Build enterprise AI applications with LlamaCloud Index and connect them to intelligent tool calling agents for complex, multi-step queries. Tutorial, Video Walkthrough.
- Delphi Case Study: See how Delphi built their "digital minds" mentorship platform using LlamaCloud's parsing capabilities for scalable document intelligence. Case Study.
✨ Framework:
- Day-Zero GPT-5 Support: OpenAI announced GPT-5 and we have immediate support - test it with Agent Maze to see how it handles complex problem-solving tasks. Agent Maze, Getting Started.
- Claude Opus 4.1 Integration: Day-zero support for Anthropic's latest Claude Opus 4.1 with search results as content blocks for better citations in agent applications. Documentation, LlamaIndex Integration.
- Realtime Voice AI Agents: Build production-grade AI systems that process live voice data from Zoom meetings using RTMS and LlamaIndex for conversation summarization and action items.
- Gemini Live Integration: New TypeScript integration for Gemini Live - add voice assistants to your web apps or chat with your terminal. Demo Code, TypeScript Docs.
✍️ Community:
- Financial Document Processing Webinar: Today! We're showing how Document Agents handle complex financial documents like 10-Ks and earnings reports. Register.
- Realtime Voice AI Workshop: Join us August 14th for a hands-on workshop on building AI agents that process live voice data from Zoom meetings using RTMS and LlamaIndex. Register.
- Novita Labs Integration: Step-by-step guide for building robust LLM applications with private data using LlamaIndex and Novita Labs' model inference capabilities. Integration Guide.
