Skip to main content

Q&A System

Submit questions to your documents and get AI-generated answers with source citations and 80% cost savings.

How it Works

When you ask a question, Hippo:
1

Semantic Search

Finds relevant chunks from your documents (not keyword matching)
2

Precision Retrieval

Retrieves only what’s needed (70% smaller context)
3

AI Generation

Generates answer using mini model with flagship accuracy
4

Source Citations

Returns answer + source documents + confidence scores
Result: 99.5% accuracy match to flagship models at 80% lower cost!

Submit Questions

Basic Q&A

Response Structure

The answer object contains:
string
The AI-generated answer to your question
string
The original question (as processed)
float
Confidence score from 0.0 to 1.0
  • 0.9+: High confidence
  • 0.7-0.9: Medium confidence
  • < 0.7: Low confidence (verify sources)
array
List of source documents cited in the answerEach source contains:
  • file_name: Name of the source file
  • file_id: Unique file identifier
  • page_number: Page where info was found
  • relevance_score: How relevant (0.0-1.0)
  • excerpt: Text snippet from source
timestamp
When the question was answered

Access Source Citations

Question History

Get All Q&A for a Chat

Get Specific Q&A by Index

Follow-up Questions

Chats remember context for follow-up questions:
Context memory: Last 10 Q&A exchanges are used for context in follow-up questions.

Question Types

Best for: Specific information retrieval
Performance: Highest accuracy (99.5%+ with clear documentation)
Best for: Step-by-step instructions
Performance: Excellent when docs contain clear procedures
Best for: Comparing options or features
Performance: Good when comparison info exists in docs
Best for: Synthesizing information
Performance: Good for overview questions across multiple sources
Best for: Quick verification
Performance: Excellent with clear documentation

Writing Effective Questions

Be Specific

✅ “What is the API rate limit for Pro plan users?” ❌ “Tell me about limits”Specific questions get specific answers

Use Natural Language

✅ “How do I reset my password?” ❌ “password reset procedure documentation”Write questions as you’d ask a person

One Question at a Time

✅ “What is the refund policy?” ❌ “What’s the refund policy and cancellation process and payment methods?”Multiple questions → Ask separately for better answers

Provide Context if Needed

✅ “In the REST API, how do I authenticate?” ❌ “How authenticate?” (ambiguous)Context helps when docs cover multiple systems

Interpreting Confidence Scores

Complete Example: Support Bot

Best Practices

Always check sources for low-confidence answers.
More specific questions → Better answers
Conversation flow leads to better understanding

Next Steps

Best Practices

Optimize answer quality and costs

Examples

Complete RAG workflow examples

Folder Management

Organize your knowledge bases