Search

NeuralRepo offers two search modes that work together to help you find ideas quickly, whether you remember the exact wording or just the general concept.

Search Modes

Semantic Search

Uses vector similarity powered by Cloudflare Vectorize and the @cf/baai/bge-m3 embedding model. Your query is converted into an embedding and compared against stored idea embeddings. Results are ranked by relevance score and reranked for quality.

Searching for “mobile habit tracker” will surface an idea titled “daily routine app for iOS” even though the words do not overlap.

Keyword Search

Uses SQLite FTS5 full-text search for exact word matching. Fast and precise when you know the specific terms you are looking for.

Searching for “React” returns only ideas that literally contain the word “React.”

Caution

Semantic search is a Pro feature. Free-tier users have access to keyword search only.

Default Behavior

When you search without specifying a mode, NeuralRepo tries semantic search first. If semantic search returns no results above the threshold, it automatically falls back to keyword search.

This gives you the best of both worlds — meaning-based discovery when it works, and exact matching as a safety net.

Searching

Web

Use the search bar at the top of the dashboard. Results appear instantly as you type, with relevance scores displayed next to each result for semantic matches.

CLI

# Search for ideas (semantic with keyword fallback)
nrepo search "distributed task queue"

# Results include relevance scores
# ID  Score  Title
# 42  0.87   Background job processing system
# 18  0.74   Message queue architecture
# 7   0.62   Async worker pattern

API

# Default (semantic with fallback)
GET /api/v1/ideas/search?q=distributed+task+queue

# Force semantic only
GET /api/v1/ideas/search?q=distributed+task+queue&mode=semantic

# Force keyword only
GET /api/v1/ideas/search?q=distributed+task+queue&mode=keyword

Response:

{
  "results": [
    {
      "id": 42,
      "title": "Background job processing system",
      "body": "...",
      "score": 0.87,
      "status": "exploring",
      "tags": ["backend", "infrastructure"]
    }
  ],
  "mode": "semantic",
  "query": "distributed task queue"
}

MCP

When connected to Claude AI via MCP, use the search_ideas tool:

"Search my NeuralRepo for ideas about authentication"

Claude will call the search_ideas tool and return matching results within the conversation.

Combining Search with Filters

Search results can be narrowed by combining the query with status and tag filters.

CLI

# Search within a specific status
nrepo search "auth" --status building

# Search within a specific tag
nrepo search "auth" --tag backend

# Combine all filters
nrepo search "auth" --status exploring --tag backend

API

GET /api/v1/ideas/search?q=auth&status=building&tag=backend

Search Threshold

The search threshold controls the minimum relevance score for semantic results. Ideas scoring below this threshold are excluded from results.

Setting	Range	Default
search_threshold	0.1 - 0.9	0.6

• Lower values (e.g., 0.3) return more results, including looser matches.
• Higher values (e.g., 0.8) return fewer results, only very close matches.

Configure the threshold in your user settings:

# Via API
curl -X PATCH https://neuralrepo.com/api/v1/settings \
  -H "Authorization: Bearer $NREPO_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"search_threshold": 0.5}'

Tip

If you find that searches return too few results, try lowering the threshold to 0.4 or 0.5. If results feel noisy and irrelevant, raise it to 0.7 or 0.8.

How Semantic Search Works

1. Your query text is sent to the @cf/baai/bge-m3 model running on Cloudflare Workers AI.
2. The model generates a vector embedding representing the meaning of your query.
3. The embedding is compared against all stored idea embeddings in Cloudflare Vectorize.
4. Results above the search threshold are returned, sorted by similarity score.
5. A reranking step refines the ordering for the final result set.

Idea embeddings are generated asynchronously when an idea is created or updated. There may be a brief delay before a brand-new idea appears in semantic search results.