Source citation in RAG responses in LangChain - Step-by-Step Execution

Concept Flow - Source citation in RAG responses

User Query

↓

Retrieve Relevant Docs

↓

Generate Answer Using Docs

↓

Attach Source Citations

↓

Return Answer + Sources

The system takes a user question, finds related documents, creates an answer using those documents, then adds citations showing where info came from.

Execution Sample

LangChain

from langchain.chains import RetrievalQA
qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
response = qa.run("What is LangChain?")
print(response)

This code runs a retrieval-augmented generation query and prints the answer with source citations.

Execution Table

Step	Action	Input	Output	Notes
1	Receive user query	"What is LangChain?"	Query stored	User question ready for retrieval
2	Retrieve documents	Query	List of relevant docs	Documents related to LangChain found
3	Generate answer	Query + docs	Answer text	Answer created using retrieved docs
4	Attach citations	Answer + docs	Answer with citations	Sources referenced in answer
5	Return response	Answer with citations	Displayed to user	Final output includes sources

💡 Process ends after returning answer with source citations to user

Variable Tracker

Variable	Start	After Step 2	After Step 3	After Step 4	Final
query	None	"What is LangChain?"	"What is LangChain?"	"What is LangChain?"	"What is LangChain?"
retrieved_docs	[]	[Doc1, Doc2]	[Doc1, Doc2]	[Doc1, Doc2]	[Doc1, Doc2]
answer_text	None	None	"LangChain is a framework..."	"LangChain is a framework... [1][2]"	"LangChain is a framework... [1][2]"

Key Moments - 2 Insights

Why do we need to attach source citations after generating the answer?

Because the answer is created from multiple documents, citations show exactly where each piece of info came from, improving trust and transparency. See execution_table step 4.

What happens if no relevant documents are found during retrieval?

The retrieved_docs list will be empty, so the answer generation may fallback to a default or say no info found. This is shown in variable_tracker after step 2.

Visual Quiz - 3 Questions

Look at the execution_table at step 3, what inputs are used to generate the answer?

A Only the user query

B Only the retrieved documents

C Both the user query and retrieved documents

D Neither query nor documents

💡 Hint

Check the 'Input' column in execution_table row for step 3

According to variable_tracker, what is the value of 'answer_text' after step 4?

A None

B "LangChain is a framework..."

C "LangChain is a framework... [1][2]"

D Empty string

💡 Hint

Look at the 'answer_text' row under 'After Step 4' in variable_tracker

If the retrieved_docs list is empty after step 2, what is likely to happen?

A Answer will be generated without sources

B Answer generation will fail immediately

C Answer will include unrelated sources

D No answer will be returned

💡 Hint

Refer to key_moments about retrieval failure and variable_tracker after step 2

Concept Snapshot

Source citation in RAG responses:
1. Receive user query
2. Retrieve relevant documents
3. Generate answer using docs
4. Attach source citations to answer
5. Return answer with sources
This improves trust by showing info origins.

Full Transcript

This visual execution shows how a retrieval-augmented generation system handles source citation. First, it receives a user query. Then it retrieves documents related to that query. Next, it generates an answer using those documents. After that, it attaches citations referencing the sources used. Finally, it returns the answer with source citations to the user. Variables like the query, retrieved documents, and answer text change step by step. Key moments include why citations are needed and what happens if no documents are found. The quiz tests understanding of inputs, variable values, and fallback behavior.