github.com/instill-ai/component@v0.16.0-beta/pkg/connector/pinecone/v0/README.mdx (about)

     1  ---
     2  title: "Pinecone"
     3  lang: "en-US"
     4  draft: false
     5  description: "Learn about how to set up a VDP Pinecone connector https://github.com/instill-ai/instill-core"
     6  ---
     7  
     8  The Pinecone component is a data connector that allows users to build and search vector datasets.
     9  It can carry out the following tasks:
    10  
    11  - [Query](#query)
    12  - [Upsert](#upsert)
    13  
    14  ## Release Stage
    15  
    16  `Alpha`
    17  
    18  ## Configuration
    19  
    20  The component configuration is defined and maintained [here](https://github.com/instill-ai/component/blob/main/pkg/connector/pinecone/v0/config/definition.json).
    21  
    22  ## Connection
    23  
    24  | Field | Field ID | Type | Note |
    25  | :--- | :--- | :--- | :--- |
    26  | API Key (required) | `api_key` | string | Fill your Pinecone AI API key. You can create a api key in [Pinecone Console](https://app.pinecone.io/) |
    27  | Pinecone Base URL (required) | `url` | string | Fill in your Pinecone base URL. It is in the form [https://index_name-project_id.svc.environment.pinecone.io] |
    28  
    29  ## Supported Tasks
    30  
    31  ### Query
    32  
    33  Retrieve the ids of the most similar items in a namespace, along with their similarity scores.
    34  
    35  | Input | ID | Type | Description |
    36  | :--- | :--- | :--- | :--- |
    37  | Task ID (required) | `task` | string | `TASK_QUERY` |
    38  | ID | `id` | string | The unique ID of the vector to be used as a query vector. If present, the vector parameter will be ignored. |
    39  | Vector (required) | `vector` | array[number] | An array of dimensions for the query vector. |
    40  | Top K (required) | `top_k` | integer | The number of results to return for each query |
    41  | Namespace | `namespace` | string | The namespace to query |
    42  | Filter | `filter` | object | The filter to apply. You can use vector metadata to limit your search. See https://www.pinecone.io/docs/metadata-filtering/. |
    43  | Minimum Score | `min_score` | number | Exclude results whose score is below this value |
    44  | Include Metadata | `include_metadata` | boolean | Indicates whether metadata is included in the response as well as the IDs |
    45  | Include Values | `include_values` | boolean | Indicates whether vector values are included in the response |
    46  
    47  | Output | ID | Type | Description |
    48  | :--- | :--- | :--- | :--- |
    49  | Namespace | `namespace` | string | The namespace of the query |
    50  | Matches | `matches` | array[object] | The matches returned for the query |
    51  
    52  ### Upsert
    53  
    54  Writes vectors into a namespace. If a new value is upserted for an existing vector id, it will overwrite the previous value.
    55  
    56  | Input | ID | Type | Description |
    57  | :--- | :--- | :--- | :--- |
    58  | Task ID (required) | `task` | string | `TASK_UPSERT` |
    59  | ID (required) | `id` | string | This is the vector's unique id |
    60  | Values (required) | `values` | array[number] | An array of dimensions for the vector to be saved |
    61  | Namespace | `namespace` | string | The namespace to query |
    62  | Metadata | `metadata` | object | The vector metadata |
    63  
    64  | Output | ID | Type | Description |
    65  | :--- | :--- | :--- | :--- |
    66  | Upserted Count | `upserted_count` | integer | Number of records modified or added |