Documents
    ↓
Chunking
    ↓
Embeddings
    ↓
Vector Store
    ↓
User Query
    ↓
Retriever
    ↓
Relevant Documents
    ↓
Summarisation Prompt
    ↓
LLM
    ↓
Final Summary

Large Document
      ↓
LLM
      ↓
Summary

Many Documents
      ↓
Find Relevant Documents
      ↓
Select Important Information
      ↓
LLM
      ↓
Focused Summary

User Query
    ↓
Embedding Model
    ↓
Query Vector
    ↓
Similarity Search
    ↓
Top-k Relevant Documents

Summarise information about RAG.

Document 1:
RAG retrieves relevant information before generation.

Document 2:
Embeddings convert text into numerical vectors.

Document 3:
Vector databases store embeddings for similarity search.

Retrieved Documents
        +
Summarisation Prompt
        ↓
Language Model
        ↓
Summary

RAG improves language model responses by retrieving relevant
information from a knowledge base before generating an answer.
Embeddings and vector stores are commonly used to find the
most relevant information.

Documents
    ↓
Chunking
    ↓
Embeddings
    ↓
Vector Store
         ↑
         │
      User Query
         │
         ↓
     Retriever
         ↓
Relevant Chunks
         ↓
Summarisation Prompt
         ↓
LLM
         ↓
Final Summary

Summarise the role of FAISS in a RAG system.

1,000 Documents
       ↓
      LLM

1,000 Documents
       ↓
Retriever
       ↓
Top 3 Relevant Documents
       ↓
LLM
       ↓
Summary

context = "\n\n".join(
    document.page_content
    for document in retrieved_documents
)

Document 1:
RAG retrieves relevant information before generation.

Document 2:
Embeddings represent text as numerical vectors.

Document 3:
FAISS performs efficient similarity search.

RAG retrieves relevant information before generation.

Embeddings represent text as numerical vectors.

FAISS performs efficient similarity search.

Summarise the following context.

Context:
{context}

Summary:

Create a concise summary using only the information
provided in the context.

Include the most important concepts.

Do not add information that is not present in the context.

Context:
{context}

Summary:

Query:
What is the role of embeddings in RAG?

Context:
Embeddings are numerical representations of text.
They allow semantic similarity comparisons between a
user query and document chunks.

Summary:
Embeddings convert text into numerical vectors that
allow a RAG system to find document chunks that are
semantically similar to a user's query.

Query
 ├── Retrieval
 │
 └── Summarisation Focus

Retrieved Documents
        ↓
Summarise
        ↓
General Summary

Summarise the following context in 3 sentences.

Context:
{context}

User Query
      ↓
Retrieve Relevant Documents
      ↓
Summarise Based on Query
      ↓
Focused Summary

Create a summary that answers the query using only
the provided context.

Query:
{query}

Context:
{context}

Summary:

Create a summary in 3 sentences.

Summarise the context in less than 100 words.

Provide the summary as bullet points.

- RAG retrieves relevant information.
- Embeddings convert text into vectors.
- FAISS performs similarity search.

Use only information provided in the context.

If the context does not contain enough information,
state that the information is unavailable.

Create a concise and accurate summary using only the
provided context.

Focus on information relevant to the user's query.

Do not add information that is not present in the
context.

If the context does not contain enough information,
say:

"I could not find enough information in the retrieved documents."

Context:
{context}

Query:
{query}

Summary:

1. Concise
2. Relevant
3. Grounded in context
4. Handles missing information

Good Retrieval
      ↓
Relevant Context
      ↓
Better Summary

Poor Retrieval
      ↓
Irrelevant Context
      ↓
Poor Summary

Retrieval Quality
        +
Generation Quality
        =
Final RAG Quality

search_kwargs={"k": 3}

k = 1
↓
Very focused context
But may miss information


k = 10
↓
More information
But may include irrelevant context

Query
  ↓
Embedding
  ↓
Query Vector
  ↓
Compare With Document Vectors
  ↓
Most Similar Documents

Large Document
      ↓
Chunking
      ↓
Chunk 1
Chunk 2
Chunk 3
      ↓
Embeddings

Chunk 1:
A B C D E

Chunk 2:
D E F G H

D E

Document 1 ──→ Summary 1
Document 2 ──→ Summary 2
Document 3 ──→ Summary 3

Summary 1
Summary 2
Summary 3
      ↓
Final Summary

Chunk
  ↓
LLM
  ↓
Partial Summary

Partial Summaries
        ↓
LLM
        ↓
Final Summary

Chunk 1
   ↓
Summary 1
   +
Chunk 2
   ↓
Updated Summary
   +
Chunk 3
   ↓
Final Summary

Initial Summary
       ↓
Add New Context
       ↓
Refine Summary
       ↓
Repeat

Document 1
Document 2
Document 3
      ↓
Combine Context
      ↓
Single LLM Prompt
      ↓
Summary

context = "\n\n".join(
    document.page_content
    for document in retrieved_documents
)

                INDEXING PHASE

Documents
    ↓
Text Chunking
    ↓
Embedding Model
    ↓
Vector Embeddings
    ↓
FAISS / Vector Store


               RETRIEVAL PHASE

User Query
    ↓
Query Embedding
    ↓
Similarity Search
    ↓
Top-k Relevant Chunks


             SUMMARISATION PHASE

Retrieved Chunks
        +
User Query
        ↓
Summarisation Prompt
        ↓
Language Model
        ↓
Grounded Summary

Documents
    ↓
Embeddings
    ↓
Vector Store
    ↓
User Query
    ↓
Retriever
    ↓
Relevant Context
    ↓
Summarisation Prompt
    ↓
LLM
    ↓
Focused Summary

1. Retrieval Quality
        +
2. Prompt Design
        ↓
Accurate and Relevant Summary

What to summarise
        +
What to focus on
        +
Expected length
        +
Output format
        +
Use only retrieved context