Pondhouse Data Blog

blog preview

Advanced RAG: Improving Retrieval-Augmented Generation with Hypothetical Document Embeddings (HyDE)

HyDE has an LLM write a fake answer document and searches with its embedding instead of the query's. How it works, plus a LlamaIndex example.

6 min read
Read Post
blog preview

GenAI: Technological Masterpiece or Ecological Disaster?

GenAI's energy use is growing fast. The IEA and de Vries numbers, plus the techniques that cut it: TPUs, MoE, distillation, MoD, layer pruning and BitNet.

16 min read
Read Post
blog preview

11 Proven Strategies to Reduce Large Language Model (LLM) Costs

Eleven ways to cut LLM costs, from shorter prompts and semantic caching to quantization, distillation, RAG and chat summaries, plus which one to try first.

15 min read
Read Post
blog preview

How to boost your database performance with OpenAIs new v3 embeddings

OpenAI's v3 embeddings can be shortened thanks to Matryoshka training. Adaptive retrieval uses that for faster vector search: 580 QPS at 99% accuracy.

10 min read
Read Post
blog preview

Introduction to Retrieval Augmented Generators (RAG): Enhancing Virtual Assistants with Domain-Specific Knowledge

How RAG works step by step: ingestion, chunking, embeddings, vector search and the LLM answer, and why it is easier to update than a fine-tuned model.

5 min read
Read Post
blog preview

Advanced RAG: Increase RAG Quality with ColBERT Reranker and llamaindex

Add a ColBERT reranker to a LlamaIndex RAG pipeline: why semantic search ranks the wrong chunks first, and the Python code to rerank them before the LLM call.

6 min read
Read Post
blog preview

Advanced RAG: Recursive Retrieval with llamaindex

Recursive retrieval in LlamaIndex links PDF tables to pandas query engines, so RAG can answer questions from table data. Step-by-step Python example.

8 min read
Read Post
blog preview

vLLM with HTTPS: Self-Host an LLM Behind a Caddy Reverse Proxy

Serve an open-source LLM with vLLM's OpenAI-compatible Docker image and put Caddy in front as a reverse proxy for automatic HTTPS with Let's Encrypt.

7 min read
Read Post
blog preview

RAG Evaluation with Ragas: How to Measure RAG Pipeline Quality

Evaluate a RAG pipeline with Ragas: generate a test set from your documents, then score faithfulness, answer relevancy, context recall and context precision.

8 min read
Read Post
blog preview

Integrating enterprise knowledge with LLMs

Fine-tuning, training your own model or RAG: how each way of adding company knowledge to an LLM works, its pros and cons, and why RAG usually wins.

9 min read
Read Post