Retrieval strategies (similarity, MMR, hybrid) in Agentic AI - Model Pipeline Trace

Model Pipeline - Retrieval strategies (similarity, MMR, hybrid)

This pipeline shows how different retrieval strategies find the best information from a large set. It uses similarity, Maximal Marginal Relevance (MMR), and a hybrid of both to pick relevant and diverse results.

Data Flow - 7 Stages

1Input Query

1 query string→Receive user question or search phrase→1 query string

"What are the benefits of exercise?"

↓

2Document Collection

1000 documents (text)→Load all documents to search from→1000 documents (text)

Articles about health, fitness, nutrition, etc.

↓

3Embedding Generation

1 query string, 1000 documents→Convert query and documents into vector embeddings→1 query vector (512 dims), 1000 document vectors (512 dims)

Query vector: [0.12, -0.03, ..., 0.45], Document vector: [0.05, 0.10, ..., -0.02]

↓

4Similarity Calculation

1 query vector, 1000 document vectors→Calculate cosine similarity scores between query and each document→1000 similarity scores (float -1 to 1)

Scores like 0.85, 0.60, 0.45 for documents

↓

5MMR Re-ranking

Top 100 documents with similarity scores→Re-rank documents balancing relevance and diversity using MMR→Top 10 documents re-ranked

Selected documents that are relevant but not too similar to each other

↓

6Hybrid Strategy

Similarity scores and MMR scores→Combine similarity and MMR scores to select final documents→Final 5 documents

Documents that are both highly relevant and diverse

↓

7Output Results

Final 5 documents→Return selected documents as search results→5 documents (text)

Articles explaining exercise benefits with different focuses

Training Trace - Epoch by Epoch

Loss
0.7 | *
0.6 |  *
0.5 |   *
0.4 |    *
0.3 |     *
0.2 |      *
    +----------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.55	Initial training with random weights, loss high, accuracy low
2	0.48	0.68	Model starts learning to rank documents better
3	0.35	0.78	Loss decreases steadily, accuracy improves
4	0.28	0.83	Model converging, better relevance and diversity balance
5	0.24	0.87	Final epoch shows good performance on validation data

Prediction Trace - 5 Layers

Layer 1: Embedding Generation

Layer 2: Similarity Calculation

Layer 3: MMR Re-ranking

Layer 4: Hybrid Strategy

Layer 5: Output Results

Model Quiz - 3 Questions

What does the similarity calculation stage do?

A Converts text into numbers

B Removes duplicate documents

C Measures how close the query and documents are in meaning

D Combines relevance and diversity scores

Key Insight

This visualization shows how combining similarity and MMR retrieval strategies helps find documents that are both relevant and diverse, improving the quality of search results.