@mastra/vectorize 0.0.0-error-handler-fix-20251020202607 → 0.0.0-esbuild-bundle-worker-20260807182016

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,149 @@
1
+ > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
2
+
3
+ # Cloudflare vector store
4
+
5
+ The CloudflareVector class provides vector search using [Cloudflare Vectorize](https://developers.cloudflare.com/vectorize/), a vector database service integrated with Cloudflare's edge network.
6
+
7
+ ## Constructor options
8
+
9
+ **accountId** (`string`): Cloudflare account ID
10
+
11
+ **apiToken** (`string`): Cloudflare API token with Vectorize permissions
12
+
13
+ ## Methods
14
+
15
+ ### `createIndex()`
16
+
17
+ **indexName** (`string`): Name of the index to create
18
+
19
+ **dimension** (`number`): Vector dimension (must match your embedding model)
20
+
21
+ **metric** (`'cosine' | 'euclidean' | 'dotproduct'`): Distance metric for similarity search (dotproduct maps to dot-product) (Default: `cosine`)
22
+
23
+ ### `upsert()`
24
+
25
+ **indexName** (`string`): Name of the index to upsert into
26
+
27
+ **vectors** (`number[][]`): Array of embedding vectors
28
+
29
+ **metadata** (`Record<string, any>[]`): Metadata for each vector
30
+
31
+ **ids** (`string[]`): Optional vector IDs (auto-generated if not provided)
32
+
33
+ ### `query()`
34
+
35
+ **indexName** (`string`): Name of the index to query
36
+
37
+ **queryVector** (`number[]`): Query vector to find similar vectors
38
+
39
+ **topK** (`number`): Number of results to return (Default: `10`)
40
+
41
+ **filter** (`Record<string, any>`): Metadata filters for the query
42
+
43
+ **includeVector** (`boolean`): Whether to include vectors in the results (Default: `false`)
44
+
45
+ ### `listIndexes()`
46
+
47
+ Returns an array of index names as strings.
48
+
49
+ ### `describeIndex()`
50
+
51
+ **indexName** (`string`): Name of the index to describe
52
+
53
+ Returns:
54
+
55
+ ```typescript
56
+ interface IndexStats {
57
+ dimension: number
58
+ count: number
59
+ metric: 'cosine' | 'euclidean' | 'dotproduct'
60
+ }
61
+ ```
62
+
63
+ ### `deleteIndex()`
64
+
65
+ **indexName** (`string`): Name of the index to delete
66
+
67
+ ### `createMetadataIndex()`
68
+
69
+ Creates an index on a metadata field to enable filtering.
70
+
71
+ **indexName** (`string`): Name of the index containing the metadata field
72
+
73
+ **propertyName** (`string`): Name of the metadata field to index
74
+
75
+ **indexType** (`'string' | 'number' | 'boolean'`): Type of the metadata field
76
+
77
+ ### `deleteMetadataIndex()`
78
+
79
+ Removes an index from a metadata field.
80
+
81
+ **indexName** (`string`): Name of the index containing the metadata field
82
+
83
+ **propertyName** (`string`): Name of the metadata field to remove indexing from
84
+
85
+ ### `listMetadataIndexes()`
86
+
87
+ Lists all metadata field indexes for an index.
88
+
89
+ **indexName** (`string`): Name of the index to list metadata indexes for
90
+
91
+ ### `updateVector()`
92
+
93
+ Updates a vector or metadata for a specific ID within an index.
94
+
95
+ **indexName** (`string`): Name of the index containing the ID to update
96
+
97
+ **id** (`string`): Unique identifier of the vector or metadata to update
98
+
99
+ **update** (`{ vector?: number[]; metadata?: Record<string, any>; }`): Object containing the vector and/or metadata to update
100
+
101
+ ### `deleteVector()`
102
+
103
+ Deletes a vector and its associated metadata for a specific ID within an index.
104
+
105
+ **indexName** (`string`): Name of the index containing the ID to delete
106
+
107
+ **id** (`string`): Unique identifier of the vector and metadata to delete
108
+
109
+ ## Response types
110
+
111
+ Query results are returned in this format:
112
+
113
+ ```typescript
114
+ interface QueryResult {
115
+ id: string
116
+ score: number
117
+ metadata: Record<string, any>
118
+ vector?: number[]
119
+ }
120
+ ```
121
+
122
+ ## Error handling
123
+
124
+ The store throws typed errors that can be caught:
125
+
126
+ ```typescript
127
+ try {
128
+ await store.query({
129
+ indexName: 'index_name',
130
+ queryVector: queryVector,
131
+ })
132
+ } catch (error) {
133
+ if (error instanceof VectorStoreError) {
134
+ console.log(error.code) // 'connection_failed' | 'invalid_dimension' | etc
135
+ console.log(error.details) // Additional error context
136
+ }
137
+ }
138
+ ```
139
+
140
+ ## Environment variables
141
+
142
+ Required environment variables:
143
+
144
+ - `CLOUDFLARE_ACCOUNT_ID`: Your Cloudflare account ID
145
+ - `CLOUDFLARE_API_TOKEN`: Your Cloudflare API token with Vectorize permissions
146
+
147
+ ## Related
148
+
149
+ - [Metadata Filters](https://mastra.ai/reference/rag/metadata-filters)