Jeffrey Rengifo
Engineering, Consulting
Jeffrey Rengifo is a software developer focusing on improving search experiences using Elasticsearch. He specializes in GenAI and aims to innovate by creating new tools to help optimize different processes and solve everyday problems.
Let the big model think, let the small model work: Splitting LLM costs in Elastic Workflows
Build an Elastic workflow that sends a data sample to a large model to propose classification labels. A human signs off, then a smaller model applies them across the full corpus.
How BBQ shrinks Jina v5 embeddings by 29x without losing recall in Elasticsearch
A hands-on test comparing BBQ and float32 vector indices in Elasticsearch, measuring memory, disk and recall@10 across five languages.
Short queries, formal documents: how HyDE improved semantic search precision by 50% in Elasticsearch
HyDE boosts semantic search precision and recall by 50% on short queries. Here's how to implement it in Elasticsearch with the Inference API and semantic_text.
Who grades the grader? LLM-as-a-Judge inside Elasticsearch Workflows
Find out if your RAG agent is ready to ship. Score it on correctness, faithfulness and retrieval quality using only Elasticsearch Workflows and two Claude models.
Talk to your Elasticsearch data: building a real-time voice agent with Google ADK and MCP in 3 components
Wire Google ADK's real-time voice streaming to your Elasticsearch data via Agent Builder's built-in MCP server; no custom integration code required.
Extract chart data standard OCR misses: Elastic Agent Builder and LlamaParse in one pipeline
Build an end-to-end pipeline that extracts structured data (including values from charts) out of complex PDFs and into Elasticsearch, ready for agent queries with ES|QL.
Your FAQ bot doesn't need a PhD: LLM query routing with Elastic Workflows
Route LLM queries by complexity using Elasticsearch search metadata: Mistral Small for FAQ questions, Claude Sonnet for multi-source synthesis.
Systematic research with LangChain's Deep Agents framework and Elasticsearch
Building a systematic research pipeline using LangChain's Deep Agents framework and Elasticsearch:
Best practices for building a modern app with vector search
Exploring six vector search tips for building modern AI search applications entirely on Elasticsearch, with an opinionated rationale at each architectural decision.
Multilingual image search with Jina CLIP v2 and Elasticsearch
Build a multilingual image search system using Jina CLIP v2 and Elasticsearch. Query your image collection in 89 languages with no translation pipeline, and use Matryoshka Representations to cut index size by 75%
How to measure and improve Elasticsearch search recall: from 0.43 to 0.75 with hybrid search
Learn how to measure and improve search recall in Elasticsearch by combining BM25 lexical search with Jina AI vector embeddings, using the rank_eval API to validate the improvement with real numbers.
From judgment lists to trained Learning to Rank (LTR) models
Learn how to transform judgment lists into training data for Learning To Rank (LTR), design effective features, and interpret what your model learned.
From Elasticsearch runtime fields to ES|QL: Adapting legacy tools to current techniques
Learn how to migrate five common Elasticsearch runtime field patterns to their ES|QL equivalents, with side-by-side code comparisons and guidance on when each approach makes sense.
Creating an Elasticsearch MCP server with TypeScript
Learn how to create an Elasticsearch MCP server with TypeScript and Claude Desktop.
Using Elasticsearch Inference API along with Hugging Face models
Learn how to connect Elasticsearch to Hugging Face models using inference endpoints, and build a multilingual blog recommendation system with semantic search and chat completions.
AI agent memory: Creating smart agents with Elasticsearch managed memory
Learn how to create smarter and more efficient AI agents by managing memory using Elasticsearch.
Building human-in-the-loop (HITL) AI agents with LangGraph and Elasticsearch
Learn what human-in-the-loop (HITL) is and how to build an HITL system with LangGraph and Elasticsearch for a flight system.
Implementing an agentic reference architecture with Elastic Agent Builder and MCP
Explore an agentic reference architecture with Elastic Agent Builder, MCP, and semantic search to build a security agent for automated threat analysis.
Building a local RAG personal knowledge assistant with LocalAI and Elasticsearch
Learn how to create a private, offline local RAG personal knowledge assistant that can summarize meetings and internal reports using e5-small for embeddings and dolphin3.0-qwen2.5-0.5b for completions in Elasticsearch.
Build a financial AI search workflow using LangGraph.js and Elasticsearch
Learn how to use LangGraph.js with Elasticsearch to build an AI-powered financial search workflow that turns natural language queries into dynamic, conditional filters for investment and market analysis.
Using LangExtract and Elasticsearch
Learn how to extract structured data from free-form text using LangExtract and store it as fields in Elasticsearch.
Using FastAPI’s WebSockets and Elasticsearch to build a real-time app
Learn how to build a real-time application using FastAPI WebSockets and Elasticsearch.
LlamaIndex and Elasticsearch Rerankers: Unbeatable simplicity
Learn how to transition from Llamaindex RankGPT reranker to Elastic built-in semantic reranker.
Building Elasticsearch APIs with FastAPI
Learn how to build an Elasticsearch API with FastAPI using Pydantic schemas and FastAPI background tasks, demonstrated with a practical example.
AI-powered dashboards: From a vision to Kibana
Generate a dashboard using an LLM to process an image and turn it into a Kibana Dashboard.
Longer context ≠ better: Why RAG still matters
Learn why the RAG strategy is still relevant and gives the most efficient and better results.
Improving Copilot capabilities using Elasticsearch
Discover how to use Elasticsearch with Microsoft 365 Copilot Chat and Copilot in Microsoft Teams.
ES|QL in JavaScript: Leveraging Apache Arrow helpers
Learn how to use ES|QL with JavaScript Apache Arrow client helpers to analyze large data sets efficiently.
Elasticsearch in JavaScript the proper way, part II
Learn about production best practices and how to run the Elasticsearch Node.js client in Serverless environments to reduce coding errors.
Elasticsearch in JavaScript the proper way, part I
Explaining how to create a production-ready Elasticsearch backend in JavaScript. Explore how to use Elasticsearch with JavaScript to create a server with different search endpoints to query Elasticsearch documents following client/server best practices.
Building a multi-agent recruitment search tool with AutoGen and Elasticsearch
Learn how to integrate Microsoft's AutoGen framework with Elasticsearch and build a multi-agent system for semantic search through a practical job matching and candidate data retrieval example.
Using LlamaIndex Workflows with Elasticsearch
Learn how to build a self-filtering Elasticsearch app using LlamaIndex Workflows with an LLM autocorrect loop and interchangeable models.
Using CrewAI tools with Elasticsearch
Learn how to create an Elasticsearch agent with CrewAI for your agent team and perform market research.
Ingesting data into Elasticsearch with BigQuery
Learn how to index and search Google BigQuery data in Elasticsearch using Python.
Exploring OpenAI CLIP alternatives
Analyzing alternatives to the OpenAI CLIP model for image-to-image, and text-to-image search.
Using Ollama with the Inference API
Learn how to integrate Ollama with Elasticsearch using the Inference API.
Are synonyms important in RAG?
Exploring the functionality of Elasticsearch synonyms in a Retrieval Augmented Generation (RAG) application.
Elastic Playground: Using Elastic connectors to chat with your data
Learn how to use Elastic connectors and Playground to chat with your data. We'll start by using connectors to search for information in different sources.
Indexing OneLake data into Elasticsearch - Part II
Second part of a two-part article to index and search OneLake data into Elastic using a Custom connector.