Embedding models for semantic search in Agentic AI - Model Pipeline Trace

Model Pipeline - Embedding models for semantic search

This pipeline uses embedding models to turn text into numbers that capture meaning. Then it finds similar texts by comparing these numbers, helping to search by meaning, not just words.

Data Flow - 6 Stages

1Raw Text Input

1000 rows x 1 column→Collect sentences or documents to search→1000 rows x 1 column

"How to bake a cake?"

↓

2Text Preprocessing

1000 rows x 1 column→Lowercase, remove punctuation, tokenize→1000 rows x variable tokens

["how", "to", "bake", "a", "cake"]

↓

3Embedding Generation

1000 rows x variable tokens→Convert tokens to fixed-size vectors using embedding model→1000 rows x 512 columns

[0.12, -0.05, 0.33, ..., 0.07]

↓

4Indexing Embeddings

1000 rows x 512 columns→Store vectors in a search index for fast similarity lookup→1000 rows x 512 columns

Vector index ready for similarity search

↓

5Query Embedding

1 row x 1 column→Preprocess and embed user query text→1 row x 512 columns

"Best cake recipes" -> [0.10, -0.02, 0.30, ..., 0.05]

↓

6Similarity Search

1 row x 512 columns (query) + 1000 rows x 512 columns (index)→Calculate cosine similarity between query and indexed embeddings→Top 5 rows x 1 column (most similar)

Top 5 similar texts with similarity scores

Training Trace - Epoch by Epoch

Loss
1.0 |****
0.8 |****
0.6 |****
0.4 |****
0.2 |****
0.0 +----
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.85	0.45	Model starts learning basic semantic relations
2	0.65	0.60	Loss decreases as embeddings capture better meaning
3	0.50	0.72	Accuracy improves, embeddings more meaningful
4	0.40	0.80	Model converging, semantic similarity clearer
5	0.35	0.85	Final embeddings ready for semantic search

Prediction Trace - 5 Layers

Layer 1: Input Query Text

Layer 2: Tokenization

Layer 3: Embedding Model

Layer 4: Similarity Calculation

Layer 5: Return Results

Model Quiz - 3 Questions

What does the embedding model output represent?

A The original text in uppercase

B A fixed-size vector capturing the meaning of the text

C A list of token counts

D The text translated to another language

Key Insight

Embedding models transform text into numbers that capture meaning, enabling search systems to find results based on semantic similarity rather than exact words. Training improves these embeddings so similar meanings get closer vectors, making search smarter and more flexible.

Practice

1. What is the main purpose of embedding models in semantic search?

easy

A. To convert text into numbers that capture meaning

B. To count the number of words in a text

C. To translate text into another language

D. To remove stop words from text

Solution

1. Step 1: Understand embedding models

   Embedding models transform text into numerical vectors that represent the meaning of the text.

2. Step 2: Identify the purpose in semantic search

   These vectors help find texts with similar meanings, even if the exact words differ.

3. Final Answer:

   To convert text into numbers that capture meaning -> Option A

4. Quick Check:

   Embedding models = convert text to meaningful numbers [OK]

Hint: Embedding models turn words into meaningful numbers [OK]

Common Mistakes:

• Thinking embeddings count words
• Confusing embeddings with translation
• Believing embeddings remove words

2. Which of the following is the correct way to get an embedding vector for a text using a model called embed_model in Python?

easy

A. embedding = embed_model.get_embedding('sample text')

B. embedding = embed_model.text_to_vector('sample text')

C. embedding = embed_model.encode('sample text')

D. embedding = embed_model.vectorize('sample text')

Solution

1. Step 1: Recall common embedding method names

   Many embedding libraries use encode to convert text to vectors.

2. Step 2: Check method correctness

   Only embed_model.encode('sample text') is a standard and valid call; others are not typical method names.

3. Final Answer:

   embedding = embed_model.encode('sample text') -> Option C

4. Quick Check:

   Use encode() to get embeddings [OK]

Hint: Use encode() method to get embeddings [OK]

Common Mistakes:

• Using non-existent methods like text_to_vector
• Confusing method names
• Forgetting to call the method with parentheses

3. Given the following Python code using an embedding model, what will be the output type of embedding?

embedding = embed_model.encode('Find similar texts')

medium

A. A list of words

B. A numeric vector (list or array) representing the text

C. A string representing the text

D. A dictionary with word counts

Solution

1. Step 1: Understand what encode() returns

   The encode() method returns a numeric vector that captures the meaning of the input text.

2. Step 2: Identify the output type

   This vector is usually a list or array of numbers, not words, strings, or dictionaries.

3. Final Answer:

   A numeric vector (list or array) representing the text -> Option B

4. Quick Check:

   encode() output = numeric vector [OK]

Hint: Embedding output is always numeric vector [OK]

Common Mistakes:

• Expecting a list of words
• Thinking output is a string
• Confusing embeddings with word counts

4. You wrote this code to get embeddings but get an error:

embedding = embed_model.encode['text to search']

What is the error and how to fix it?

medium

A. Add a return statement before encode

B. Change 'text to search' to a list of words

C. Remove the encode method and use embed_model directly

D. Use parentheses () instead of brackets [] to call encode method

Solution

1. Step 1: Identify the syntax error

   Methods in Python are called with parentheses (), not brackets []. Using brackets causes a TypeError.

2. Step 2: Correct the method call

   Replace encode['text to search'] with encode('text to search') to fix the error.

3. Final Answer:

   Use parentheses () instead of brackets [] to call encode method -> Option D

4. Quick Check:

   Method calls need () not [] [OK]

Hint: Call methods with () not [] [OK]

Common Mistakes:

• Using brackets [] instead of parentheses ()
• Passing wrong argument types
• Trying to call method without parentheses

5. You want to build a semantic search system that finds documents similar in meaning to a query. Which approach best uses embedding models for this task?

hard

A. Convert all documents and the query to embeddings, then find documents with closest vectors

B. Count keyword frequency in documents and query, then match counts

C. Translate documents to another language before searching

D. Sort documents alphabetically and pick the first matches

Solution

1. Step 1: Understand semantic search with embeddings

   Semantic search uses embeddings to represent meaning, so comparing vectors finds similar meaning.

2. Step 2: Identify the correct approach

   Converting documents and query to embeddings and finding closest vectors is the correct method for semantic search.

3. Final Answer:

   Convert all documents and the query to embeddings, then find documents with closest vectors -> Option A

4. Quick Check:

   Semantic search = compare embedding vectors [OK]

Hint: Compare embeddings of query and documents for semantic search [OK]

Common Mistakes:

• Using keyword counts instead of embeddings
• Translating text unnecessarily
• Sorting alphabetically instead of by meaning