Create Vector Store with OpenAI (ChatGPT) API on New Row Custom Query from PostgreSQL API

Pipedream makes it easy to connect APIs for OpenAI (ChatGPT), PostgreSQL and 2,800+ other apps remarkably fast.

Trigger workflow on

New Row Custom Query from the PostgreSQL API

Next, do this

Create Vector Store with the OpenAI (ChatGPT) API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a PostgreSQL trigger and OpenAI (ChatGPT) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Row Custom Query trigger
1. Connect your PostgreSQL account
2. Configure Polling Interval
3. Select a Schema
4. Select a Table
5. Select a Column
6. Configure SQL Query
7. Optional- Configure Values
Configure the Create Vector Store action
1. Connect your OpenAI (ChatGPT) account
2. Optional- Select one or more File IDs
3. Optional- Configure Name
4. Optional- Configure Expiration Days
5. Optional- Configure Metadata
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Row Custom Query on PostgreSQL

Description:Emit new event when new rows are returned from a custom query that you provide. [See the documentation](https://node-postgres.com/features/queries)

Version:2.0.8

Key:postgresql-new-row-custom-query

View on GitHub

PostgreSQL Overview#

On Pipedream, you can leverage the PostgreSQL app to create workflows that automate database operations, synchronize data across platforms, and react to database events in real-time. Think handling new row entries, updating records from webhooks, or even compiling reports on a set schedule. Pipedream's serverless platform provides a powerful way to connect PostgreSQL with a variety of apps, enabling you to create tailored automation that fits your specific needs.

Trigger Code#

import common from "../common.mjs"; export default { ...common, name: "New Row Custom Query", key: "postgresql-new-row-custom-query", description: "Emit new event when new rows are returned from a custom query that you provide. [See the documentation](https://node-postgres.com/features/queries)", version: "2.0.8", type: "source", dedupe: "unique", props: { ...common.props, schema: { propDefinition: [ common.props.postgresql, "schema", ], }, table: { propDefinition: [ common.props.postgresql, "table", (c) => ({ schema: c.schema, }), ], }, column: { propDefinition: [ common.props.postgresql, "column", (c) => ({ table: c.table, schema: c.schema, }), ], }, query: { propDefinition: [ common.props.postgresql, "query", ], description: "Specify the query to select new or updated rows since the last poll. For example, `SELECT * FROM users WHERE country = 'US'`", }, values: { propDefinition: [ common.props.postgresql, "values", ], }, }, hooks: { async deploy() { if (this.values && !Array.isArray(this.values)) { throw new Error("No valid values provided. The values property must be an array."); } const numberOfValues = this.query?.match(/\$/g)?.length || 0; if (this.values && this.values.length !== numberOfValues) { throw new Error("The number of values provided does not match the number of values in the query."); } const isColumnUnique = await this.isColumnUnique(this.schema, this.table, this.column); if (!isColumnUnique) { throw new Error("The column selected contains duplicate values. Column must be unique"); } }, }, methods: { ...common.methods, generateMeta(row, column) { return { id: row[column], summary: "New Row", ts: Date.now(), }; }, }, async run() { const rows = await this.postgresql.executeQuery({ text: this.query, values: this.values, }); for (const row of rows) { const meta = this.generateMeta(row, this.column); this.$emit(row, meta); } }, };

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
PostgreSQL	`postgresql`	`app`	This component uses the PostgreSQL app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
Polling Interval	`timer`	`$.interface.timer`	Pipedream will poll the API on this schedule
Schema	`schema`	`string`	Select a value from the drop down menu.
Table	`table`	`string`	Select a value from the drop down menu.
Column	`column`	`string`	Select a value from the drop down menu.
SQL Query	`query`	`string`	Specify the query to select new or updated rows since the last poll. For example, `SELECT * FROM users WHERE country = 'US'`
Values	`values`	`string[]`	List of values represented in your SQL Query above

Trigger Authentication#

PostgreSQL uses API keys for authentication. When you connect your PostgreSQL account, Pipedream securely stores the keys so you can easily authenticate to PostgreSQL APIs in both code and no-code steps.

Connecting to Restricted Databases

Either enable the shared static IP for this account below, or configure a VPC to deploy any workflow in your workspace to a private network with a dedicated static IP. Learn more in our docs

SSL Setup

Configure SSL on your PostgreSQL database by providing the CA (Certificate Authority), and choosing between Full Verification, Verify Certificate Authority (CA), or Skip Verification. Skipping verification is not recommended as this has serious security implications

About PostgreSQL#

PostgreSQL is a free and open-source relational database management system emphasizing extensibility and SQL compliance.

Action#

Create Vector Store on OpenAI (ChatGPT)

Description:Create a vector store. [See the documentation](https://platform.openai.com/docs/api-reference/vector-stores/create)

Version:0.0.7

Key:openai-create-vector-store

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Action Code#

import openai from "../../openai.app.mjs"; export default { key: "openai-create-vector-store", name: "Create Vector Store", description: "Create a vector store. [See the documentation](https://platform.openai.com/docs/api-reference/vector-stores/create)", version: "0.0.7", annotations: { destructiveHint: false, openWorldHint: true, readOnlyHint: false, }, type: "action", props: { openai, fileIds: { propDefinition: [ openai, "fileId", ], type: "string[]", label: "File IDs", description: "An array of File IDs that the vector store should use", optional: true, reloadProps: true, }, name: { type: "string", label: "Name", description: "Name of the vector store", optional: true, }, expiryDays: { type: "integer", label: "Expiration Days", description: "The number of days after the `last_active_at` time that the vector store will expire", optional: true, }, metadata: { type: "object", label: "Metadata", description: "Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format", optional: true, }, }, additionalProps() { const props = {}; if (!this.fileIds?.length) { return props; } props.chunkingStrategy = { type: "string", label: "Chunking Strategy", description: "The chunking strategy used to chunk the file(s)", options: [ "auto", "static", ], optional: true, reloadProps: true, }; if (this?.chunkingStrategy === "static") { props.maxChunkSizeTokens = { type: "integer", label: "Max Chunk Size Tokens", description: "The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`.", default: 800, optional: true, }; props.chunkOverlapTokens = { type: "integer", label: "Chunk Overlap Tokens", description: "The number of tokens that overlap between chunks. The default value is `400`. Note that the overlap must not exceed half of max_chunk_size_tokens.", default: 400, optional: true, }; } return props; }, async run({ $ }) { const response = await this.openai.createVectorStore({ $, data: { file_ids: this.fileIds, name: this.name, expires_after: this.expiryDays && { anchor: "last_active_at", days: this.expiryDays, }, chunking_strategy: this.chunkingStrategy && { type: this.chunkingStrategy, static: this.chunkingStrategy === "static" ? { max_chunk_size_tokens: this.maxChunkSizeTokens, chunk_overlap_tokens: this.chunkOverlapTokens, } : undefined, }, metadata: this.metadata, }, }); $.export("$summary", `Successfully created vector store with ID: ${response.id}`); return response; }, };

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
File IDs	`fileIds`	`string[]`	Select a value from the drop down menu.
Name	`name`	`string`	Name of the vector store
Expiration Days	`expiryDays`	`integer`	The number of days after the `last_active_at` time that the vector store will expire
Metadata	`metadata`	`object`	Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format