voyageai-cli 1.20.6 → 1.22.0

package/src/lib/templates/nextjs/page-search.jsx.tpl

@@ -0,0 +1,147 @@
+/**
+ * Search Page (MUI)
+ * Generated by vai v{{vaiVersion}} on {{generatedAt}}
+ */
+
+'use client';
+
+import { useState } from 'react';
+import {
+  Box,
+  Container,
+  TextField,
+  Button,
+  Card,
+  CardContent,
+  Typography,
+  List,
+  ListItem,
+  Chip,
+  CircularProgress,
+  Alert,
+  InputAdornment,
+} from '@mui/material';
+import SearchIcon from '@mui/icons-material/Search';
+
+export default function SearchPage() {
+  const [query, setQuery] = useState('');
+  const [results, setResults] = useState([]);
+  const [loading, setLoading] = useState(false);
+  const [error, setError] = useState(null);
+  const [meta, setMeta] = useState(null);
+
+  const handleSearch = async (e) => {
+    e.preventDefault();
+    if (!query.trim()) return;
+
+    setLoading(true);
+    setError(null);
+
+    try {
+      const response = await fetch('/api/search', {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ query, limit: 5 }),
+      });
+
+      if (!response.ok) {
+        const data = await response.json();
+        throw new Error(data.error || 'Search failed');
+      }
+
+      const data = await response.json();
+      setResults(data.results);
+      setMeta(data.meta);
+    } catch (err) {
+      setError(err.message);
+      setResults([]);
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  return (
+    <Container maxWidth="md" sx={{ py: 4 }}>
+      <Typography variant="h4" component="h1" gutterBottom>
+        Semantic Search
+      </Typography>
+      
+      <Typography variant="body1" color="text.secondary" sx={{ mb: 3 }}>
+        Search your documents using {{model}} embeddings
+        {{#if rerank}} with {{rerankModel}} reranking{{/if}}.
+      </Typography>
+
+      <Box component="form" onSubmit={handleSearch} sx={{ mb: 4 }}>
+        <TextField
+          fullWidth
+          value={query}
+          onChange={(e) => setQuery(e.target.value)}
+          placeholder="Enter your search query..."
+          variant="outlined"
+          InputProps={{
+            startAdornment: (
+              <InputAdornment position="start">
+                <SearchIcon />
+              </InputAdornment>
+            ),
+            endAdornment: (
+              <InputAdornment position="end">
+                <Button
+                  type="submit"
+                  variant="contained"
+                  disabled={loading || !query.trim()}
+                >
+                  {loading ? <CircularProgress size={24} /> : 'Search'}
+                </Button>
+              </InputAdornment>
+            ),
+          }}
+        />
+      </Box>
+
+      {error && (
+        <Alert severity="error" sx={{ mb: 3 }}>
+          {error}
+        </Alert>
+      )}
+
+      {meta && (
+        <Box sx={{ mb: 2, display: 'flex', gap: 1 }}>
+          <Chip label={`${results.length} results`} size="small" />
+          <Chip label={`${meta.took}ms`} size="small" variant="outlined" />
+          <Chip label={meta.model} size="small" variant="outlined" />
+        </Box>
+      )}
+
+      <List>
+        {results.map((result, index) => (
+          <ListItem key={index} sx={{ px: 0 }}>
+            <Card sx={{ width: '100%' }}>
+              <CardContent>
+                <Box sx={{ display: 'flex', justifyContent: 'space-between', mb: 1 }}>
+                  <Typography variant="subtitle2" color="text.secondary">
+                    {result.metadata?.source || 'Document'}
+                  </Typography>
+                  <Chip
+                    label={`Score: ${result.score.toFixed(3)}`}
+                    size="small"
+                    color={result.score > 0.8 ? 'success' : 'default'}
+                  />
+                </Box>
+                <Typography variant="body2" sx={{ whiteSpace: 'pre-wrap' }}>
+                  {result.text}
+                </Typography>
+              </CardContent>
+            </Card>
+          </ListItem>
+        ))}
+      </List>
+
+      {results.length === 0 && !loading && query && !error && (
+        <Typography color="text.secondary" align="center">
+          No results found for "{query}"
+        </Typography>
+      )}
+    </Container>
+  );
+}

package/src/lib/templates/nextjs/route-ingest.js.tpl

@@ -0,0 +1,114 @@
+/**
+ * Ingest API Route Handler
+ * Generated by vai v{{vaiVersion}} on {{generatedAt}}
+ * 
+ * POST /api/ingest
+ */
+
+import { NextResponse } from 'next/server';
+import { embed } from '@/lib/voyage';
+import { insertDocuments } from '@/lib/mongodb';
+
+/**
+ * Chunk text using recursive splitting.
+ */
+function chunkText(text, size = {{chunkSize}}, overlap = {{chunkOverlap}}) {
+  const separators = ['\n\n', '\n', '. ', ' '];
+  
+  function splitRecursive(text, sepIndex = 0) {
+    if (text.length <= size) {
+      const trimmed = text.trim();
+      return trimmed ? [trimmed] : [];
+    }
+    
+    if (sepIndex >= separators.length) {
+      const chunks = [];
+      let start = 0;
+      while (start < text.length) {
+        const chunk = text.slice(start, start + size).trim();
+        if (chunk) chunks.push(chunk);
+        start += size - overlap;
+      }
+      return chunks;
+    }
+    
+    const separator = separators[sepIndex];
+    const parts = text.split(separator);
+    const chunks = [];
+    let current = '';
+    
+    for (const part of parts) {
+      const potential = current ? current + separator + part : part;
+      if (potential.length <= size) {
+        current = potential;
+      } else {
+        if (current) chunks.push(...splitRecursive(current, sepIndex + 1));
+        current = part;
+      }
+    }
+    
+    if (current) chunks.push(...splitRecursive(current, sepIndex + 1));
+    return chunks;
+  }
+  
+  return splitRecursive(text);
+}
+
+export async function POST(request) {
+  const start = Date.now();
+  
+  try {
+    const body = await request.json();
+    const { text, metadata = {} } = body;
+    
+    if (!text || typeof text !== 'string') {
+      return NextResponse.json(
+        { error: 'Text is required' },
+        { status: 400 }
+      );
+    }
+    
+    // Chunk the text
+    const chunks = chunkText(text);
+    
+    if (chunks.length === 0) {
+      return NextResponse.json({
+        success: true,
+        chunks: 0,
+        tokens: 0,
+        took: Date.now() - start,
+      });
+    }
+    
+    // Embed all chunks
+    const { embeddings, usage } = await embed(chunks, { inputType: 'document' });
+    
+    // Prepare documents
+    const documents = chunks.map((chunk, i) => ({
+      text: chunk,
+      embedding: embeddings[i],
+      metadata: {
+        ...metadata,
+        source: metadata.source || 'api',
+        chunkIndex: i,
+        totalChunks: chunks.length,
+      },
+    }));
+    
+    // Insert into MongoDB
+    await insertDocuments(documents);
+    
+    return NextResponse.json({
+      success: true,
+      chunks: chunks.length,
+      tokens: usage.total_tokens,
+      took: Date.now() - start,
+    });
+  } catch (error) {
+    console.error('Ingest error:', error);
+    return NextResponse.json(
+      { error: error.message },
+      { status: 500 }
+    );
+  }
+}

package/src/lib/templates/nextjs/route-search.js.tpl

@@ -0,0 +1,97 @@
+/**
+ * Search API Route Handler
+ * Generated by vai v{{vaiVersion}} on {{generatedAt}}
+ * 
+ * POST /api/search
+ */
+
+import { NextResponse } from 'next/server';
+import { embedQuery{{#if rerank}}, rerank{{/if}} } from '@/lib/voyage';
+import { vectorSearch } from '@/lib/mongodb';
+
+export async function POST(request) {
+  const start = Date.now();
+  
+  try {
+    const body = await request.json();
+    const { query, limit = 5, includeContext = false, filter } = body;
+    
+    if (!query || typeof query !== 'string') {
+      return NextResponse.json(
+        { error: 'Query is required' },
+        { status: 400 }
+      );
+    }
+    
+{{#if rerank}}
+    const candidates = body.candidates || 20;
+{{/if}}
+    
+    // Step 1: Embed the query
+    const queryEmbedding = await embedQuery(query);
+    
+    // Step 2: Vector search
+{{#if rerank}}
+    const searchResults = await vectorSearch(queryEmbedding, {
+      limit: candidates,
+      filter,
+    });
+{{else}}
+    const searchResults = await vectorSearch(queryEmbedding, {
+      limit,
+      filter,
+    });
+{{/if}}
+    
+    if (searchResults.length === 0) {
+      return NextResponse.json({
+        results: [],
+        meta: {
+          model: '{{model}}',
+          took: Date.now() - start,
+        },
+      });
+    }
+    
+{{#if rerank}}
+    // Step 3: Rerank for better relevance
+    const documents = searchResults.map(r => r.document.text);
+    const { results: reranked } = await rerank(query, documents, { topK: limit });
+    
+    const results = reranked.map(r => ({
+      text: searchResults[r.index].document.text,
+      score: r.relevanceScore,
+      metadata: searchResults[r.index].document.metadata,
+    }));
+{{else}}
+    const results = searchResults.map(r => ({
+      text: r.document.text,
+      score: r.score,
+      metadata: r.document.metadata,
+    }));
+{{/if}}
+    
+    const response = {
+      results,
+      meta: {
+        model: '{{model}}',
+{{#if rerank}}
+        rerankModel: '{{rerankModel}}',
+{{/if}}
+        took: Date.now() - start,
+      },
+    };
+    
+    if (includeContext) {
+      response.context = results.map(r => r.text).join('\n\n---\n\n');
+    }
+    
+    return NextResponse.json(response);
+  } catch (error) {
+    console.error('Search error:', error);
+    return NextResponse.json(
+      { error: error.message },
+      { status: 500 }
+    );
+  }
+}

package/src/lib/templates/nextjs/theme.js.tpl

@@ -0,0 +1,84 @@
+/**
+ * MUI Theme Configuration
+ * Generated by vai v{{vaiVersion}} on {{generatedAt}}
+ */
+
+'use client';
+
+import { createTheme } from '@mui/material/styles';
+
+// MongoDB-inspired color palette
+const palette = {
+  primary: {
+    main: '#00ED64',      // MongoDB Green
+    light: '#4DFF94',
+    dark: '#00B84A',
+    contrastText: '#000',
+  },
+  secondary: {
+    main: '#001E2B',      // MongoDB Dark
+    light: '#1C3A4B',
+    dark: '#000F17',
+    contrastText: '#fff',
+  },
+  background: {
+    default: '#FAFAFA',
+    paper: '#FFFFFF',
+  },
+  text: {
+    primary: '#001E2B',
+    secondary: '#5C6C75',
+  },
+};
+
+export const theme = createTheme({
+  palette,
+  typography: {
+    fontFamily: '"Inter", "Roboto", "Helvetica", "Arial", sans-serif',
+    h1: {
+      fontWeight: 700,
+    },
+    h2: {
+      fontWeight: 600,
+    },
+    h3: {
+      fontWeight: 600,
+    },
+    h4: {
+      fontWeight: 600,
+    },
+  },
+  shape: {
+    borderRadius: 8,
+  },
+  components: {
+    MuiButton: {
+      styleOverrides: {
+        root: {
+          textTransform: 'none',
+          fontWeight: 600,
+        },
+        contained: {
+          boxShadow: 'none',
+          '&:hover': {
+            boxShadow: 'none',
+          },
+        },
+      },
+    },
+    MuiCard: {
+      styleOverrides: {
+        root: {
+          boxShadow: '0 1px 3px rgba(0,0,0,0.12), 0 1px 2px rgba(0,0,0,0.06)',
+        },
+      },
+    },
+    MuiChip: {
+      styleOverrides: {
+        root: {
+          fontWeight: 500,
+        },
+      },
+    },
+  },
+});

package/src/lib/templates/python/README.md.tpl

@@ -0,0 +1,145 @@
+# {{projectName}}
+
+A semantic search API powered by Voyage AI embeddings and MongoDB Atlas Vector Search.
+
+## Configuration
+
+| Setting | Value |
+|---------|-------|
+| Embedding Model | `{{model}}` |
+| Dimensions | {{dimensions}} |
+| Database | `{{db}}` |
+| Collection | `{{collection}}` |
+| Vector Index | `{{index}}` |
+{{#if rerank}}
+| Rerank Model | `{{rerankModel}}` |
+{{/if}}
+
+## Setup
+
+### 1. Create virtual environment
+
+```bash
+python -m venv venv
+source venv/bin/activate  # On Windows: venv\Scripts\activate
+```
+
+### 2. Install dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+### 3. Configure environment
+
+Copy `.env.example` to `.env` and fill in your credentials:
+
+```bash
+cp .env.example .env
+```
+
+Required variables:
+- `VOYAGE_API_KEY` - Your Voyage AI API key from [dash.voyageai.com](https://dash.voyageai.com)
+- `MONGODB_URI` - Your MongoDB Atlas connection string
+
+### 4. Create vector index
+
+In MongoDB Atlas, create a vector search index on your collection:
+
+```json
+{
+  "fields": [
+    {
+      "type": "vector",
+      "path": "{{field}}",
+      "numDimensions": {{dimensions}},
+      "similarity": "cosine"
+    }
+  ]
+}
+```
+
+Name the index `{{index}}`.
+
+### 5. Start the server
+
+```bash
+python app.py
+
+# For production
+gunicorn -w 4 -b 0.0.0.0:3000 app:app
+```
+
+## API Endpoints
+
+### POST /api/search
+
+Search for relevant documents.
+
+```bash
+curl -X POST http://localhost:3000/api/search \
+  -H "Content-Type: application/json" \
+  -d '{"query": "How does vector search work?", "limit": 5}'
+```
+
+Response:
+```json
+{
+  "results": [
+    {
+      "text": "Vector search uses...",
+      "score": 0.95,
+      "metadata": {"source": "docs/guide.md"}
+    }
+  ],
+  "meta": {
+    "model": "{{model}}",
+    "took": 123
+  }
+}
+```
+
+### POST /api/ingest
+
+Ingest text documents.
+
+```bash
+curl -X POST http://localhost:3000/api/ingest \
+  -H "Content-Type: application/json" \
+  -d '{"text": "Your document content...", "metadata": {"source": "api"}}'
+```
+
+### GET /api/health
+
+Check API health and database connection.
+
+```bash
+curl http://localhost:3000/api/health
+```
+
+## Project Structure
+
+```
+{{projectName}}/
+├── app.py              # Flask application
+├── voyage_client.py    # Voyage AI API client
+├── mongo_client.py     # MongoDB connection helper
+├── chunker.py          # Text chunking utilities
+├── requirements.txt
+├── .env.example
+└── README.md
+```
+
+## Chunking Configuration
+
+Documents are chunked with the following settings:
+
+| Setting | Value |
+|---------|-------|
+| Strategy | `{{chunkStrategy}}` |
+| Chunk Size | {{chunkSize}} characters |
+| Overlap | {{chunkOverlap}} characters |
+
+---
+
+Generated by [vai](https://github.com/mrlynn/voyageai-cli) v{{vaiVersion}}