Requires an AI subscription

You can open this panel by clicking the corresponding tab lower down on the right-hand side of the app.

Main Features:

• Query input - Type your questions in plain English
• Automatic chunking - Sources split into searchable pieces when needed
• Similarity slider - Control search precision (0.1-0.9)
• Max Chunks slider - Maximum number of the most relevant chunks to send to the AI
• Prompt history - Navigate previous questions with prev/next buttons. See these tips

Search Modes#

AI Answers offers two search modes, automatically optimized based on your data size:

Full Sources Mode#

Searches the complete text of your sources (documents/interviews).

How it works:

1. Type a question about the text of the currently selected sources
2. System automatically chunks sources into searchable segments (if not already done)
3. Searches through document chunks using AI embeddings and semantic similarity
4. Most relevant chunks are sent to AI for analysis
5. AI generates answers with supporting quotes from your sources

Question expansion and HyDE (Hypothetical Document Embeddings)

Rather than just using the user's question to match against chunks, we call genAI as preparation and ask it to produce:

1. 8 question variants: short phrases likely to appear directly in source texts containing answers
2. 8 answer variants: different longer and shorter phrases which could contain possible answers, substantially and linguistically different from one another

We match each of these phrases against the chosen chunks and make a sum of the scores per chunk, to then select the top n according the the max_chunks slider.

So for example if the user asks what is the connection between money and happiness, the AI produces question variants like:

• having money, being joyful
• being wealthy
• being happy
• connection between money and happiness

And answer variants like:

• financial security enables emotional wellbeing
• wealth contributes to life satisfaction
• economic resources support positive mental health outcomes

Best for: Exploratory questions about raw text, finding themes not yet coded, discovering new patterns.

Link Contexts Mode#

Searches only through your coded causal links and their surrounding context (the quote + 3 sentences before/after).

How it works:

1. Gets filtered links from your current filter pipeline (respects Sources dropdown and all Source Groups filters)
2. For each link, extracts the selected quote plus surrounding context
3. Organizes contexts by source, with source metadata (title, custom columns)
4. For ≤500 links: Sends all contexts directly to AI
5. For >500 links: Uses backend semantic search to find most relevant contexts
6. Embeddings generated server-side (via find-relevant-contexts edge function)
7. Also uses question expansion (see above)
8. Similarity calculation done server-side using cosine similarity
9. Only relevant context indices returned to frontend
10. No memory/computation overhead in browser
11. AI analyzes contexts showing cause → effect relationships
12. AI uses the cause/effect labels in its narrative (ignoring any original labels if links were recoded)

Context format sent to AI:

```