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
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 confidence0.7-0.9: 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 filefile_id: Unique file identifierpage_number: Page where info was foundrelevance_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
Factual Questions
Factual Questions
Best for: Specific information retrievalPerformance: Highest accuracy (99.5%+ with clear documentation)
How-To Questions
How-To Questions
Best for: Step-by-step instructionsPerformance: Excellent when docs contain clear procedures
Comparison Questions
Comparison Questions
Best for: Comparing options or featuresPerformance: Good when comparison info exists in docs
Summary Questions
Summary Questions
Best for: Synthesizing informationPerformance: Good for overview questions across multiple sources
Yes/No Questions
Yes/No Questions
Best for: Quick verificationPerformance: 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
Verify Low-Confidence Answers
Verify Low-Confidence Answers
Rephrase if Needed
Rephrase if Needed
Add Documents if Information Missing
Add Documents if Information Missing
Use Follow-ups for Clarification
Use Follow-ups for Clarification
Next Steps
Best Practices
Optimize answer quality and costs
Examples
Complete RAG workflow examples
Folder Management
Organize your knowledge bases

