@jerryjliu0: I'm glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the o…
Summary
Jerry Liu highlights the engineering challenges of productionizing agentic retrieval systems, emphasizing that success depends on careful tuning of chunking, synchronization, reranking, and tool API design rather than novel techniques.
View Cached Full Text
Cached at: 07/20/26, 09:36 PM
I’m glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the outer models/harnesses are getting better every day.
Making agentic retrieval work in production doesn’t necessarily require groundbreaking new techniques around retrieval or planning. This article shows that you do need to spend engineering time tuning chunking, synchronization, reranking, tool API design, permissioning, and more. Some interesting tidbits:
- Concatenating onto existing Slack threads as one contiguous chunk with heuristics for determining additional relevant context
- Real-time updates for Slack
- Separate chunking/updates for codebases
- The discovery that hybrid search works well (not like this was a super new realization, but always good to validate and understand the specific parameters they tweaked)
- Having natural guardrails on which data sources are relevant for which projects
Building simple retrieval is easy, building production retrieval is hard. We had to deal with a lot of these challenges when productionizing our own Index feature within LlamaParse.
Similar Articles
@DataScienceDojo: The retrieval step in a RAG system is only as good as the chunks feeding it — and most teams don't think carefully abou…
This article discusses five chunking strategies for RAG systems, highlighting the tradeoffs between retrieval precision and reasoning context, and emphasizing that proper chunking is crucial for effective retrieval.
@jerryjliu0: We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent…
LlamaIndex has created a Retrieval Harness for modern agentic retrieval, providing a persistent data pipeline for connecting, indexing, and querying large knowledge bases with tools like semantic search and regex grep, allowing agents to autonomously navigate knowledge bases.
@akshay_pachaar: Google and Anthropic agree on one thing about retrieval. They both moved it out of the app and turned it into a standal…
Google and Anthropic both treat retrieval as a standalone service invoked by agents, moving away from naive one-time RAG pipelines. The post explains how a continuous ingestion layer and structured retrieval units fix stale embeddings and coupled infrastructure, reportedly reducing corpus size 40x and improving vector relevance 2.3x.
@LearnWithBrij: Stop building RAG like it’s still 2022. Chunk → Embed → Retrieve → Generate That pipeline works… until you try to ship …
A thread explaining the four essential layers for building production-grade RAG systems beyond simple chunk-embed-retrieve-generate: intelligent query routing, advanced indexing, multi-type retrieval, and continuous evaluation.
@jerryjliu0: 3 years ago I gave a talk at the first @aiDotEngineer conference on "Advanced RAG" techniques in order to work around t…
Jerry Liu reflects on the evolution of RAG techniques over three years, noting a shift from naive RAG to agent-based abstractions and from code-defined to goal-defined agents.