Files
cim_summary/backend/try-create-function.js
Jon df079713c4 feat: Complete cloud-native CIM Document Processor with full BPCP template
🌐 Cloud-Native Architecture:
- Firebase Functions deployment (no Docker)
- Supabase database (replacing local PostgreSQL)
- Google Cloud Storage integration
- Document AI + Agentic RAG processing pipeline
- Claude-3.5-Sonnet LLM integration

 Full BPCP CIM Review Template (7 sections):
- Deal Overview
- Business Description
- Market & Industry Analysis
- Financial Summary (with historical financials table)
- Management Team Overview
- Preliminary Investment Thesis
- Key Questions & Next Steps

🔧 Cloud Migration Improvements:
- PostgreSQL → Supabase migration complete
- Local storage → Google Cloud Storage
- Docker deployment → Firebase Functions
- Schema mapping fixes (camelCase/snake_case)
- Enhanced error handling and logging
- Vector database with fallback mechanisms

📄 Complete End-to-End Cloud Workflow:
1. Upload PDF → Document AI extraction
2. Agentic RAG processing → Structured CIM data
3. Store in Supabase → Vector embeddings
4. Auto-generate PDF → Full BPCP template
5. Download complete CIM review

🚀 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-08-01 17:51:45 -04:00

104 lines
3.2 KiB
JavaScript

const { createClient } = require('@supabase/supabase-js');
const fs = require('fs');
// Load environment variables
require('dotenv').config();
const supabaseUrl = process.env.SUPABASE_URL;
const supabaseServiceKey = process.env.SUPABASE_SERVICE_KEY;
const supabase = createClient(supabaseUrl, supabaseServiceKey);
async function tryCreateFunction() {
console.log('🚀 Attempting to create vector search function...');
const functionSQL = `
CREATE OR REPLACE FUNCTION match_document_chunks(
query_embedding VECTOR(1536),
match_threshold FLOAT DEFAULT 0.7,
match_count INTEGER DEFAULT 10
)
RETURNS TABLE (
id UUID,
document_id TEXT,
content TEXT,
metadata JSONB,
chunk_index INTEGER,
similarity FLOAT
)
LANGUAGE SQL STABLE
AS $$
SELECT
document_chunks.id,
document_chunks.document_id,
document_chunks.content,
document_chunks.metadata,
document_chunks.chunk_index,
1 - (document_chunks.embedding <=> query_embedding) AS similarity
FROM document_chunks
WHERE document_chunks.embedding IS NOT NULL
AND 1 - (document_chunks.embedding <=> query_embedding) > match_threshold
ORDER BY document_chunks.embedding <=> query_embedding
LIMIT match_count;
$$;`;
// Try direct SQL execution
try {
const { data, error } = await supabase.rpc('query', {
query: functionSQL
});
if (error) {
console.log('❌ Direct query failed:', error.message);
} else {
console.log('✅ Function created via direct query!');
}
} catch (e) {
console.log('❌ Direct query method not available');
}
// Alternative: Try creating via Edge Functions (if available)
try {
const response = await fetch(`${supabaseUrl}/rest/v1/rpc/sql`, {
method: 'POST',
headers: {
'apikey': supabaseServiceKey,
'Authorization': `Bearer ${supabaseServiceKey}`,
'Content-Type': 'application/json'
},
body: JSON.stringify({ query: functionSQL })
});
if (response.ok) {
console.log('✅ Function created via REST API!');
} else {
console.log('❌ REST API method failed:', response.status);
}
} catch (e) {
console.log('❌ REST API method not available');
}
// Test if function exists now
console.log('🧪 Testing if function exists...');
const testEmbedding = new Array(1536).fill(0.1);
const { data, error } = await supabase.rpc('match_document_chunks', {
query_embedding: testEmbedding,
match_threshold: 0.5,
match_count: 5
});
if (error) {
console.log('❌ Function still not available:', error.message);
console.log('');
console.log('📋 Manual steps required:');
console.log('1. Go to https://supabase.com/dashboard/project/gzoclmbqmgmpuhufbnhy/sql');
console.log('2. Run the SQL from vector_function.sql');
console.log('3. Then test with: node test-vector-search.js');
} else {
console.log('✅ Function is working!');
console.log('Found', data ? data.length : 0, 'results');
}
}
tryCreateFunction();