Combining retrieved context with LLM in Prompt Engineering / GenAI - Model Pipeline Trace

Model Pipeline - Combining retrieved context with LLM

This pipeline shows how a language model uses extra information found by searching to give better answers. It first finds helpful text, then mixes it with the question, and finally the model learns to give improved replies.

Data Flow - 4 Stages

1Input Question

1 question string→User asks a question to the system→1 question string

"What is the capital of France?"

↓

2Context Retrieval

1 question string→Search external documents or database to find relevant text→1 question string + retrieved context text

"Paris is the capital city of France."

↓

3Context Integration

1 question string + retrieved context text→Combine question and context into one input for the language model→1 combined input string

"Question: What is the capital of France? Context: Paris is the capital city of France."

↓

4Language Model Processing

1 combined input string→The language model processes the combined input to generate an answer→1 answer string

"The capital of France is Paris."

Training Trace - Epoch by Epoch

Loss
1.2 |*       
1.0 | *      
0.8 |  *     
0.6 |   *    
0.4 |    *   
0.2 |     *  
0.0 +--------
      1 2 3 4 5
       Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Model starts learning to use context but predictions are rough.
2	0.9	0.60	Model improves understanding of context relevance.
3	0.7	0.75	Better integration of question and context seen.
4	0.5	0.85	Model confidently uses retrieved context to answer.
5	0.4	0.90	Training converges with high accuracy and low loss.

Prediction Trace - 4 Layers

Layer 1: Input Question

Layer 2: Context Retrieval

Layer 3: Context Integration

Layer 4: Language Model Processing

Model Quiz - 3 Questions

What is the main purpose of retrieving context before using the language model?

A To replace the language model completely

B To provide extra information that helps the model answer better

C To make the input shorter

D To confuse the model with more data

Key Insight

Combining retrieved context with a language model helps the model give more accurate and relevant answers by providing it with useful background information. Training shows steady improvement as the model learns to use this extra context effectively.

Practice

1. Why do we combine retrieved context with a large language model (LLM)?

easy

A. To give the model extra information it did not learn before

B. To make the model run faster

C. To reduce the size of the model

D. To replace the model's training data

Solution

1. Step 1: Understand the purpose of retrieved context

   Retrieved context provides additional information that the model might not have seen during training.

2. Step 2: Connect context to model output quality

   Providing this extra information helps the model give better and more accurate answers.

3. Final Answer:

   To give the model extra information it did not learn before -> Option A

4. Quick Check:

   Extra info improves answers = D [OK]

Hint: Extra info helps model answer better [OK]

Common Mistakes:

• Thinking context speeds up the model
• Believing context shrinks the model size
• Assuming context replaces training data

2. Which of the following is the correct way to combine retrieved context with an LLM prompt?

easy

A. prompt = question * context

B. prompt = question + context

C. prompt = context + ' ' + question

D. prompt = context - question

Solution

1. Step 1: Understand prompt construction

   The prompt should start with the context followed by the question to give the model relevant info first.

2. Step 2: Check syntax correctness

   Using string concatenation with '+' is correct; multiplication or subtraction of strings is invalid.

3. Final Answer:

   prompt = context + ' ' + question -> Option C

4. Quick Check:

   Context before question with '+' = A [OK]

Hint: Concatenate context and question with + [OK]

Common Mistakes:

• Putting question before context
• Using * or - operators on strings
• Not adding space between context and question

3. Given the code below, what will be the output?

context = 'The capital of France is Paris.'
question = 'What is the capital of France?'
prompt = context + ' ' + question
response = llm.generate(prompt)
print(response)

Assuming llm.generate() returns the model's answer, what is the likely output?

medium

A. Paris

B. London

C. I don't know

D. Error: undefined variable

Solution

1. Step 1: Analyze the prompt content

   The prompt includes the context 'The capital of France is Paris.' followed by the question.

2. Step 2: Predict model output based on context

   The model uses the context to answer correctly with 'Paris'.

3. Final Answer:

   Paris -> Option A

4. Quick Check:

   Context guides answer = Paris [OK]

Hint: Context gives correct answer to question [OK]

Common Mistakes:

• Ignoring context and guessing wrong
• Assuming code error without cause
• Thinking model says 'I don't know'

4. You wrote this code to combine context with a question:

context = 'Water boils at 100 degrees Celsius.'
question = 'At what temperature does water boil?'
prompt = question + ' ' + context
response = llm.generate(prompt)
print(response)

Why might the model give a less accurate answer?

medium

A. Because the context is missing important info

B. Because the question comes before the context, confusing the model

C. Because the model cannot handle string concatenation

D. Because the prompt is too short

Solution

1. Step 1: Check prompt order

   The prompt puts the question before the context, which may confuse the model about what info to use.

2. Step 2: Understand best practice

   Context should come first to provide relevant info before the question.

3. Final Answer:

   Because the question comes before the context, confusing the model -> Option B

4. Quick Check:

   Context before question improves accuracy = B [OK]

Hint: Put context before question in prompt [OK]

Common Mistakes:

• Thinking model can't concatenate strings
• Assuming context lacks info
• Believing prompt length is the issue

5. You want to build a system that answers questions about a company's products using an LLM. You have a large product manual. What is the best way to combine the manual with the LLM to get accurate answers?

hard

A. Train a new LLM from scratch on the manual

B. Feed the entire manual as a prompt to the LLM every time

C. Only ask the question without any manual context

D. Retrieve relevant sections from the manual and add them as context before the question in the prompt

Solution

1. Step 1: Consider prompt size limits

   Feeding the entire manual is too large and inefficient for the LLM prompt.

2. Step 2: Use retrieval to select relevant info

   Retrieving relevant sections and adding them as context helps the model answer accurately without overload.

3. Step 3: Evaluate other options

   Asking without context misses info; training new LLM is costly and unnecessary.

4. Final Answer:

   Retrieve relevant sections from the manual and add them as context before the question in the prompt -> Option D

5. Quick Check:

   Relevant context retrieval + LLM = A [OK]

Hint: Retrieve relevant info, then prompt LLM [OK]

Common Mistakes:

• Trying to input entire manual at once
• Ignoring context and asking only question
• Thinking retraining is always needed