multimodal-agent-workshop

โ˜… 17 Open GitHub โ†—

๐Ÿ–ผ๏ธ Workshop: Build a multimodal AI agent with Haystack & GPT-4o โ€” featuring image understanding, document retrieval, conversational memory, and human-in-the-loop safety controls

Explore Similar Repositories

WorldKV : Official implementation of "WorldKV: Efficient World Memory with World Retrieval and Compression"
MemSifter : MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
MRAD : Official implementation of โ€œMRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrievalโ€ (ICLR 2026)
VestPocket : ๐Ÿ‘œ Single-file persisted lookup key/value database contained in a pure .NET 7.0+ library. All records persisted are kept in-memory for fast retrieval and synchronized with the file.
Efficient-SAM2 : [ICLR 2026] The official implementation of "Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval"
// repository documentation