Chat using File Search with OpenAI (ChatGPT) API on New Row 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 from the PostgreSQL API

Next, do this

Chat using File Search 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 trigger
1. Connect your PostgreSQL account
2. Configure Polling Interval
3. Select a Schema
4. Select a Table
5. Optional- Select a Column
Configure the Chat using File Search action
1. Connect your OpenAI (ChatGPT) account
2. Configure alert
3. Select a Model
4. Select a Vector Store ID
5. Configure Chat Input
6. Optional- Configure Instructions
7. Optional- Configure Include Search Results
8. Optional- Configure Max Number of Results
9. Optional- Configure Metadata Filtering
10. Optional- Configure Previous Response ID
11. Optional- Select a Truncation
12. Optional- Select a Response Format
13. Optional- Configure Skip This Step
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 on PostgreSQL

Description:Emit new event when a new row is added to a table. [See the documentation](https://node-postgres.com/features/queries)

Version:3.0.8

Key:postgresql-new-row

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", key: "postgresql-new-row", description: "Emit new event when a new row is added to a table. [See the documentation](https://node-postgres.com/features/queries)", version: "3.0.8", 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) => ({ schema: c.schema, table: c.table, }), ], description: "An ID or timestamp column where new rows will always contain larger values than the previous row. Defaults to the table's primary key.", optional: true, }, }, hooks: { /** If column prop is left blank, get the table's primary key to use * for ordering and deduping. */ async deploy() { const column = this.column ? this.column : await this.postgresql.getPrimaryKey(this.table, this.schema); const isColumnUnique = await this.isColumnUnique(this.schema, this.table, column); if (!isColumnUnique) { throw new Error("The column selected contains duplicate values. Column must be unique"); } this._setColumn(column); await this.initialRows(this.schema, this.table, column); }, }, methods: { ...common.methods, _getColumn() { return this.db.get("column"); }, _setColumn(column) { this.db.set("column", column); }, generateMeta(row, column) { return { id: row[column], summary: "New Row Added", ts: Date.now(), }; }, }, async run() { const column = this._getColumn(); await this.newRows(this.schema, this.table, column); }, };

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.

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#

Chat using File Search on OpenAI (ChatGPT)

Description:Chat with your files knowledge base (vector stores). [See the documentation](https://platform.openai.com/docs/guides/tools-file-search)

Version:0.0.8

Key:openai-chat-using-file-search

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"; import common from "../common/common.mjs"; import constants from "../../common/constants.mjs"; export default { ...common, name: "Chat using File Search", version: "0.0.8", annotations: { destructiveHint: false, openWorldHint: true, readOnlyHint: true, }, key: "openai-chat-using-file-search", description: "Chat with your files knowledge base (vector stores). [See the documentation](https://platform.openai.com/docs/guides/tools-file-search)", type: "action", props: { openai, alert: { type: "alert", alertType: "info", content: "To use this action, you need to have set up a knowledge base in a vector store and uploaded files to it. [More infomation here](https://platform.openai.com/docs/guides/tools-file-search?lang=javascript#overview).", }, modelId: { propDefinition: [ openai, "chatCompletionModelId", ], }, vectorStoreId: { propDefinition: [ openai, "vectorStoreId", ], description: "The identifier of a vector store. Currently supports only one vector store at a time", }, input: { type: "string", label: "Chat Input", description: "Text inputs to the model used to generate a response", }, instructions: { type: "string", label: "Instructions", description: "Inserts a system (or developer) message as the first item in the model's context", optional: true, }, includeSearchResults: { type: "boolean", label: "Include Search Results", description: "Include the search results in the response", default: false, optional: true, }, maxNumResults: { type: "integer", label: "Max Number of Results", description: "Customize the number of results you want to retrieve from the vector store", optional: true, }, metadataFiltering: { type: "boolean", label: "Metadata Filtering", description: "Configure how the search results are filtered based on file metadata", optional: true, reloadProps: true, }, previousResponseId: { type: "string", label: "Previous Response ID", description: "The unique ID of the previous response to the model. Use this to create multi-turn conversations", optional: true, }, truncation: { type: "string", label: "Truncation", description: "Specifies the truncation mode for the response if it's larger than the context window size", optional: true, default: "auto", options: [ "auto", "disabled", ], }, responseFormat: { type: "string", label: "Response Format", description: "- **Text**: Returns unstructured text output.\n- **JSON Schema**: Enables you to define a [specific structure for the model's output using a JSON schema](https://platform.openai.com/docs/guides/structured-outputs?api-mode=responses).", options: [ "text", "json_schema", ], default: "text", optional: true, reloadProps: true, }, skipThisStep: { type: "boolean", label: "Skip This Step", description: "Pass in a boolean custom expression to skip this step's execution at runtime", optional: true, default: false, }, }, additionalProps() { const { modelId, metadataFiltering, responseFormat, } = this; const props = {}; if (this.openai.isReasoningModel(modelId)) { props.reasoningEffort = { type: "string", label: "Reasoning Effort", description: "Constrains effort on reasoning for reasoning models", optional: true, options: [ "low", "medium", "high", ], }; // aparrently not supported yet as of 12/march/2025 // props.generateSummary = { // type: "string", // label: "Generate Reasoning Summary", // description: "A summary of the reasoning performed by the model", // optional: true, // options: [ // "concise", // "detailed", // ], // }; } // TODO: make this configuration user-friendly // https://platform.openai.com/docs/guides/retrieval?attributes-filter-example=region#attribute-filtering if (metadataFiltering) { props.filters = { type: "object", label: "Filters", description: "Filter the search results based on file metadata. [See the documentation here](https://platform.openai.com/docs/guides/retrieval#attribute-filtering)", }; } if (responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value) { props.jsonSchema = { type: "string", label: "JSON Schema", description: "Define the schema that the model's output must adhere to. [Generate one here](https://platform.openai.com/docs/guides/structured-outputs/supported-schemas).", }; } return props; }, methods: { ...common.methods, }, async run({ $ }) { if (this.skipThisStep) { $.export("$summary", "Step execution skipped"); return; } const data = { model: this.modelId, input: this.input, instructions: this.instructions, previous_response_id: this.previousResponseId, truncation: this.truncation, tools: [ { type: "file_search", vector_store_ids: [ this.vectorStoreId, ], max_num_results: this.maxNumResults, }, ], }; if (this.includeSearchResults) { data.include = [ "output[*].file_search_call.search_results", ]; } if (this.filters) { data.tools[0].filters = this.filters; } if (this.openai.isReasoningModel(this.modelId) && this.reasoningEffort) { data.reasoning = { ...data.reasoning, effort: this.reasoningEffort, }; } if (this.openai.isReasoningModel(this.modelId) && this.generateSummary) { data.reasoning = { ...data.reasoning, generate_summary: this.generateSummary, }; } if (this.responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value) { try { data.text = { format: { type: this.responseFormat, ...JSON.parse(this.jsonSchema), }, }; } catch (error) { throw new Error("Invalid JSON format in the provided JSON Schema"); } } const response = await this.openai.responses({ $, data, }); if (response) { $.export("$summary", `Successfully sent chat with id ${response.id}`); $.export("chat_responses", response.output); } 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.
Model	`modelId`	`string`	Select a value from the drop down menu.
Vector Store ID	`vectorStoreId`	`string`	Select a value from the drop down menu.
Chat Input	`input`	`string`	Text inputs to the model used to generate a response
Instructions	`instructions`	`string`	Inserts a system (or developer) message as the first item in the model's context
Include Search Results	`includeSearchResults`	`boolean`	Include the search results in the response
Max Number of Results	`maxNumResults`	`integer`	Customize the number of results you want to retrieve from the vector store
Metadata Filtering	`metadataFiltering`	`boolean`	Configure how the search results are filtered based on file metadata
Previous Response ID	`previousResponseId`	`string`	The unique ID of the previous response to the model. Use this to create multi-turn conversations
Truncation	`truncation`	`string`	Select a value from the drop down menu:`autodisabled`
Response Format	`responseFormat`	`string`	Select a value from the drop down menu:`textjson_schema`
Skip This Step	`skipThisStep`	`boolean`	Pass in a boolean custom expression to skip this step's execution at runtime