Reranking Retrieved Results
Boost RAG accuracy by reranking initial vector search candidates with cross-encoder models before passing context to the LLM.
Reranking Retrieved Results is a free Vector Databases: Pinecone, Weaviate & pgvector lesson on CoddyKit — lesson 4 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the Vector Databases: Pinecone, Weaviate & pgvector learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.
The Reranking Idea
Vector search is fast but approximate. Reranking takes the top candidates and reorders them with a more accurate, slower model — the two-stage retrieve-then-rerank pattern.
Bi-Encoder vs Cross-Encoder
Bi-encoders embed query and document separately (fast, used for retrieval). Cross-encoders score query+document together (slow, far more accurate) — ideal for reranking a small set.
Two-Stage Pipeline
Step 1: retrieve top 50 with the vector DB. Step 2: rerank those 50, keep the top 5. You get cross-encoder quality at near vector-search speed.
candidates = vector_db.search(query, k=50)
ranked = reranker.rank(query, candidates)
top = ranked[:5]Using a Cross-Encoder
A cross-encoder takes pairs and outputs a relevance score. Higher means more relevant.
from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')
scores = model.predict([(query, doc) for doc in candidates])Sorting by Score
Pair each document with its score and sort descending to produce the final order.
ranked = sorted(zip(candidates, scores), key=lambda x: x[1], reverse=True)
for doc, score in ranked[:5]:
print(round(score, 3), doc[:40])Hosted Reranking APIs
Services like Cohere Rerank and Jina offer hosted rerankers via API, removing the need to self-host a model.
POST /v1/rerank
{ "query": "...", "documents": [...], "top_n": 5 }Choosing Candidate Count
Retrieve enough candidates that the true best answer is in the set (high recall), but not so many that reranking gets slow. 20-100 is typical.
Latency Trade-offs
Reranking adds latency proportional to candidate count. Cache results, batch the cross-encoder calls, and tune the candidate count to your SLA.
Reranking + Filters
Apply metadata filters during retrieval, then rerank only the filtered set. This keeps the reranker focused on valid candidates.
Measuring the Gain
Compare nDCG or hit rate with and without reranking on a labeled set. Reranking commonly delivers a large accuracy boost on noisy corpora.
When to Skip It
If your corpus is small and clean, or latency is critical, plain vector search may suffice. Reranking pays off most on large, diverse datasets.
Quick Check
Test your reranking knowledge.
Recap
You learned the retrieve-then-rerank pattern, the difference between bi- and cross-encoders, how to score and sort candidates, and when reranking is worth its latency cost.
Frequently asked questions
Is the “Reranking Retrieved Results” lesson free?
Yes — the full text of “Reranking Retrieved Results” is free to read here on the web, and the Vector Databases: Pinecone, Weaviate & pgvector course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the Vector Databases: Pinecone, Weaviate & pgvector course, upgrade to CoddyKit PRO.
What will I learn in “Reranking Retrieved Results”?
Boost RAG accuracy by reranking initial vector search candidates with cross-encoder models before passing context to the LLM. You practise Vector Databases: Pinecone, Weaviate & pgvector with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.
Do I need any experience to start Vector Databases: Pinecone, Weaviate & pgvector?
No prior experience is required. Vector Databases: Pinecone, Weaviate & pgvector on CoddyKit is structured for beginners through advanced learners; this is — lesson 4 of 4, so you can start here or from the beginning and move at your own pace.
How long does the “Reranking Retrieved Results” lesson take?
Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.
Can I write and run code in this Vector Databases: Pinecone, Weaviate & pgvector lesson?
Yes. Every Vector Databases: Pinecone, Weaviate & pgvector lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.
All lessons in this course
- Query Transformation Techniques
- Multi-Stage RAG Pipelines
- Evaluating RAG System Performance
- Reranking Retrieved Results