proomt

Search

Search posts, papers, and topics

All posts

TemporalCornelia Davis11 min readintermediate

Durable RAG and agents: MongoDB and Temporal doing it better together

Summary

This article describes how MongoDB Atlas and Temporal combine to build durable RAG and agent systems. MongoDB handles data, embeddings, and vector search, while Temporal ensures reliable data ingestion pipelines and resilient, long-running agent execution, preventing data loss and re-computation.

  • MongoDB Atlas consolidates operational data, embeddings, vector search, and agent memory into one platform.
  • Temporal provides durable execution for RAG ingestion pipelines, ensuring no data deltas are lost and handling failures automatically.
  • Temporal makes multi-step AI agent reasoning loops resilient to crashes, resuming execution without re-burning tokens.
  • Using Temporal for durability can eliminate the need for Kafka in ingestion pipelines, simplifying architecture.

Engineers building production-grade RAG or agentic AI systems will find this useful for understanding how to achieve reliability and simplify their data and orchestration layers.

7/10

Related reading

  1. Chaining Activities — from text to vectors

    This post details how Temporal Activities orchestrate an RAG pipeline, from text embedding to vector storage, ensuring PII compliance and idempotency. It covers using an on-premise embedding model, caching vectors in Redis, and upserting to Pinecone with robust retry mechanisms.

    Temporaltemporal.io5 min
  2. Durable Digest: August highlights

    Temporal’s August digest rolls out a suite of new features: Serverless Workers for AWS Lambda (public preview), Projects for organizing Cloud resources, Standalone Nexus Operations, Google GenAI and Deep Agents integrations, Activity Operations and Workflow Pause controls, poller autoscaling GA, and .NET/TypeScript Nexus SDKs. It also adds a Web UI news feed, new tutorials, validated patterns, an…

    Temporaltemporal.io5 min
  3. How LlamaIndex uses Temporal to scale reliable document orchestration

    LlamaIndex migrated from RabbitMQ to Temporal for orchestrating complex, multi-stage document processing workflows, scaling to tens of millions of pages daily. This shift enabled them to replace ad-hoc state management and concurrency controls with Temporal's durable execution and workflow primitives, improving reliability and resource efficiency.

    Temporaltemporal.io7 min