diff --git a/apps/docs/components/Navigation/NavigationMenu/NavigationMenu.constants.ts b/apps/docs/components/Navigation/NavigationMenu/NavigationMenu.constants.ts index 98dd7069470..869e8ec0c56 100644 --- a/apps/docs/components/Navigation/NavigationMenu/NavigationMenu.constants.ts +++ b/apps/docs/components/Navigation/NavigationMenu/NavigationMenu.constants.ts @@ -1747,6 +1747,10 @@ export const ai = { url: '/guides/ai/vector-indexes', items: vectorIndexItems, }, + { + name: 'Automatic embeddings', + url: '/guides/ai/automatic-embeddings', + }, { name: 'Engineering for scale', url: '/guides/ai/engineering-for-scale', diff --git a/apps/docs/content/guides/ai/automatic-embeddings.mdx b/apps/docs/content/guides/ai/automatic-embeddings.mdx new file mode 100644 index 00000000000..48f1f7389c6 --- /dev/null +++ b/apps/docs/content/guides/ai/automatic-embeddings.mdx @@ -0,0 +1,817 @@ +--- +id: 'ai-automatic-embeddings' +title: 'Automatic embeddings' +description: 'Automate embedding generation and updates in Postgres' +sidebar_label: 'Automatic embeddings' +--- + +Vector embeddings enable powerful [semantic search](/docs/guides/ai/semantic-search) capabilities in Postgres, but managing them alongside your content has traditionally been complex. This guide demonstrates how to automate embedding generation and updates using Supabase [Edge Functions](/docs/guides/functions), [pgmq](/docs/guides/database/extensions/pgmq), [pg_net](/docs/guides/database/extensions/pg_net), and [pg_cron](/docs/guides/cron). + +## Understanding the challenge + +When implementing semantic search with pgvector, developers typically need to: + +1. Generate embeddings via an external API (like OpenAI) +2. Store these embeddings alongside the content +3. Keep embeddings in sync when content changes +4. Handle failures and retries in the embedding generation process + +While Postgres [full-text search](/docs/guides/database/full-text-search) can handle this internally through synchronous calls to `to_tsvector` and [triggers](https://www.postgresql.org/docs/current/textsearch-features.html#TEXTSEARCH-UPDATE-TRIGGERS), semantic search requires asynchronous API calls to a provider like OpenAI to generate vector embeddings. This guide demonstrates how to use triggers, queues, and Supabase Edge Functions to bridge this gap. + +## Understanding the architecture + +We'll leverage the following Postgres and Supabase features to create the automated embedding system: + +1. [pgvector](/docs/guides/database/extensions/pgvector): Stores and queries vector embeddings +1. [pgmq](/docs/guides/queues): Queues embedding generation requests for processing and retries +1. [pg_net](/docs/guides/database/extensions/pg_net): Handles asynchronous HTTP requests to Edge Functions directly from Postgres +1. [pg_cron](/docs/guides/cron): Automatically processes and retries embedding generations +1. [Triggers](/docs/guides/database/postgres/triggers): Detects content changes and enqueues embedding generation requests +1. [Edge Functions](/docs/guides/functions): Generates embeddings via an API like OpenAI (customizable) + +We'll design the system to: + +1. Be generic, so that it can be used with any table and content. This allows you to configure embeddings in multiple places, each with the ability to customize the input used for embedding generation. These will all use the same queue infrastructure and Edge Function to generate the embeddings. + +1. Handle failures gracefully, by retrying failed jobs and providing detailed information about the status of each job. + +## Implementation + +We'll start by setting up the infrastructure needed to queue and process embedding generation requests. Then we'll create an example table with triggers to enqueue these embedding requests whenever content is inserted or updated. + +### Step 1: Enable extensions + +First, let's enable the required extensions: + + + + +```sql +-- For vector operations +create extension if not exists vector +with + schema extensions; + +-- For queueing and processing jobs +-- (pgmq will create its own schema) +create extension if not exists pgmq; + +-- For async HTTP requests +create extension if not exists pg_net +with + schema extensions; + +-- For scheduled processing and retries +-- (pg_cron will create its own schema) +create extension if not exists pg_cron; + +-- For clearing embeddings during updates +create extension if not exists hstore +with + schema extensions; +``` + +Even though the SQL code is `create extension`, this is the equivalent of "enabling the extension". +To disable an extension, call `drop extension`. + + + + +1. Go to the [Extensions](/dashboard/project/_/database/extensions) page in the Dashboard. +2. Search for and enable the following extensions: + - `vector` + - `pgmq` + - `pg_net` + - `pg_cron` + - `hstore` + + + + +### Step 2: Create utility functions + +Before we set up our embedding logic, we need to create some utility functions: + +```sql +-- Schema for utility functions +create schema util; + +-- Utility function to get the Supabase project URL (required for Edge Functions) +create function util.project_url() +returns text +language plpgsql +security definer +as $$ +declare + secret_value text; +begin + -- Retrieve the project URL from Vault + select decrypted_secret into secret_value from vault.decrypted_secrets where name = 'project_url'; + return secret_value; +end; +$$; + +-- Generic function to invoke any Edge Function +create or replace function util.invoke_edge_function( + name text, + body jsonb, + timeout_milliseconds int = 5 * 60 * 1000 -- default 5 minute timeout +) +returns void +language plpgsql +as $$ +declare + headers_raw text; + auth_header text; +begin + -- If we're in a PostgREST session, reuse the request headers for authorization + headers_raw := current_setting('request.headers', true); + + -- Only try to parse if headers are present + auth_header := case + when headers_raw is not null then + (headers_raw::json->>'authorization') + else + null + end; + + -- Perform async HTTP request to the edge function + perform net.http_post( + url => util.project_url() || '/functions/v1/' || name, + headers => jsonb_build_object( + 'Content-Type', 'application/json', + 'Authorization', auth_header + ), + body => body, + timeout_milliseconds => timeout_milliseconds + ); +end; +$$; + +-- Generic trigger function to clear a column on update +create or replace function util.clear_column() +returns trigger +language plpgsql as $$ +declare + clear_column text := TG_ARGV[0]; +begin + NEW := NEW #= hstore(clear_column, NULL); + return NEW; +end; +$$; +``` + +Here we create: + +- A schema `util` to store utility functions. +- A function to retrieve the Supabase project URL from [Vault](/docs/guides/database/vault). We'll add this secret next. +- A generic function to invoke any Edge Function with a given name and request body. +- A generic trigger function to clear a column on update. This function accepts the column name as an argument and sets it to `NULL` in the `NEW` record. We'll explain how to use this function later. + +Every project has a unique API URL that is required to invoke Edge Functions. Let's go ahead and add the project URL secret to Vault depending on your environment. + +When working with a local Supabase stack, add the following to your `supabase/seed.sql` file: + +```sql +select + vault.create_secret('http://api.supabase.internal:8000', 'project_url'); +``` + +When deploying to the cloud platform, open the [SQL editor](/dashboard/project/_/sql/new) and run the following, replacing `` with your [project's API URL](/dashboard/project/_/settings/api): + +```sql +select + vault.create_secret('', 'project_url'); +``` + +### Step 3: Create queue and triggers + +Our goal is to automatically generate embeddings whenever content is inserted or updated within a table. We can use triggers and queues to achieve this. Our approach is to automatically queue embedding jobs whenever records are inserted or updated in a table, then process them asynchronously using a cron job. If a job fails, it will remain in the queue and be retried in the next scheduled task. + +First we create a `pgmq` queue for processing embedding requests: + +```sql +-- Queue for processing embedding jobs +select pgmq.create('embedding_jobs'); +``` + +Next we create a trigger function to queue embedding jobs. We'll use this function to handle both insert and update events: + +```sql +-- Generic trigger function to queue embedding jobs +create or replace function util.queue_embeddings() +returns trigger +language plpgsql +as $$ +declare + content_function text = TG_ARGV[0]; + embedding_column text = TG_ARGV[1]; +begin + perform pgmq.send( + queue_name => 'embedding_jobs', + msg => jsonb_build_object( + 'id', NEW.id, + 'schema', TG_TABLE_SCHEMA, + 'table', TG_TABLE_NAME, + 'contentFunction', content_function, + 'embeddingColumn', embedding_column + ) + ); + return NEW; +end; +$$; +``` + +Our `util.queue_embeddings` trigger function is generic and can be used with any table and content function. It accepts two arguments: + +1. `content_function`: The name of a function that returns the text content to be embedded. The function should accept a single row as input and return text (see the `embedding_input` example). + + This allows you to customize the text input passed to the embedding model - for example, you could concatenate multiple columns together like `title` and `content` and use the result as input. + +2. `embedding_column`: The name of the destination column where the embedding will be stored. + +Note that the `util.queue_embeddings` trigger function requires a `for each row` clause to work correctly. See [Usage](#usage) for an example of how to use this trigger function with your table. + +Next we'll create a function to process the embedding jobs. This function will read jobs from the queue, group them into batches, and invoke the Edge Function to generate embeddings. We'll use `pg_cron` to schedule this function to run every 10 seconds. + +```sql +-- Function to process embedding jobs from the queue +create or replace function util.process_embeddings( + batch_size int = 10, + max_requests int = 10, + timeout_milliseconds int = 5 * 60 * 1000 -- default 5 minute timeout +) +returns void +language plpgsql +as $$ +declare + job_batches jsonb[]; + batch jsonb; +begin + with + -- First get jobs and assign batch numbers + numbered_jobs as ( + select + message || jsonb_build_object('jobId', msg_id) as job_info, + (row_number() over (order by 1) - 1) / batch_size as batch_num + from pgmq.read( + queue_name => 'embedding_jobs', + vt => timeout_milliseconds / 1000, + qty => max_requests * batch_size + ) + ), + -- Then group jobs into batches + batched_jobs as ( + select + jsonb_agg(job_info) as batch_array, + batch_num + from numbered_jobs + group by batch_num + ) + -- Finally aggregate all batches into array + select array_agg(batch_array) + from batched_jobs + into job_batches; + + -- Invoke the embed edge function for each batch + foreach batch in array job_batches loop + perform util.invoke_edge_function( + name => 'embed', + body => batch, + timeout_milliseconds => timeout_milliseconds + ); + end loop; +end; +$$; + +-- Schedule the embedding processing +select + cron.schedule( + 'process-embeddings', + '10 seconds', + $$ + select util.process_embeddings(); + $$ + ); +``` + +Let's discuss some common questions about this approach: + +#### Why not generate all embeddings in a single Edge Function request? + +While this is possible, it can lead to long processing times and potential timeouts. Batching allows us to process multiple embeddings concurrently and handle failures more effectively. + +#### Why not one request per row? + +This approach can lead to API rate limiting and performance issues. Batching provides a balance between efficiency and reliability. + +#### Why queue requests instead of processing them immediately? + +Queuing allows us to handle failures gracefully, retry requests, and manage concurrency more effectively. Specifically we are using `pgmq`'s visibility timeouts to ensure that failed requests are retried. + +#### How do visibility timeouts work? + +Every time we read a message from the queue, we set a visibility timeout which tells `pgmq` to hide the message from other readers for a certain period. If the Edge Function fails to process the message within this period, the message becomes visible again and will be retried by the next scheduled task. + +#### How do we handle retries? + +We use `pg_cron` to schedule a task that reads messages from the queue and processes them. If the Edge Function fails to process a message, it becomes visible again after a timeout and can be retried by the next scheduled task. + +#### Is 10 seconds a good interval for processing? + +This interval is a good starting point, but you may need to adjust it based on your workload and the time it takes to generate embeddings. You can adjust the `batch_size`, `max_requests`, and `timeout_milliseconds` parameters to optimize performance. + +### Step 4: Create the Edge Function + +Finally we'll create the Edge Function to generate embeddings. We'll use OpenAI's API in this example, but you can replace it with any other embedding generation service. + +Use the Supabase CLI to create a new Edge Function: + +```bash +supabase functions new embed +``` + +This will create a new directory `supabase/functions/embed` with an `index.ts` file. Replace the contents of this file with the following: + +_supabase/functions/embed/index.ts_: + +```typescript +// Setup type definitions for built-in Supabase Runtime APIs +import 'jsr:@supabase/functions-js/edge-runtime.d.ts' + +// We'll use the OpenAI API to generate embeddings +import OpenAI from 'jsr:@openai/openai' + +import { z } from 'npm:zod' + +// We'll make a direct Postgres connection to update the document +import postgres from 'https://deno.land/x/postgresjs@v3.4.5/mod.js' + +// Initialize OpenAI client +const openai = new OpenAI({ + // We'll need to manually set the `OPENAI_API_KEY` environment variable + apiKey: Deno.env.get('OPENAI_API_KEY'), +}) + +// Initialize Postgres client +const sql = postgres( + // `SUPABASE_DB_URL` is a built-in environment variable + Deno.env.get('SUPABASE_DB_URL')! +) + +const jobSchema = z.object({ + jobId: z.number(), + id: z.number(), + schema: z.string(), + table: z.string(), + contentFunction: z.string(), + embeddingColumn: z.string(), +}) + +const failedJobSchema = jobSchema.extend({ + error: z.string(), +}) + +type Job = z.infer +type FailedJob = z.infer + +type Row = { + id: string + content: unknown +} + +const QUEUE_NAME = 'embedding_jobs' + +// Listen for HTTP requests +Deno.serve(async (req) => { + if (req.method !== 'POST') { + return new Response('expected POST request', { status: 405 }) + } + + if (req.headers.get('content-type') !== 'application/json') { + return new Response('expected json body', { status: 400 }) + } + + // Use Zod to parse and validate the request body + const parseResult = z.array(jobSchema).safeParse(await req.json()) + + if (parseResult.error) { + return new Response(`invalid request body: ${parseResult.error.message}`, { + status: 400, + }) + } + + const pendingJobs = parseResult.data + + // Track jobs that completed successfully + const completedJobs: Job[] = [] + + // Track jobs that failed due to an error + const failedJobs: FailedJob[] = [] + + async function processJobs() { + let currentJob: Job | undefined + + while ((currentJob = pendingJobs.shift()) !== undefined) { + try { + await processJob(currentJob) + completedJobs.push(currentJob) + } catch (error) { + failedJobs.push({ + ...currentJob, + error: error instanceof Error ? error.message : JSON.stringify(error), + }) + } + } + } + + try { + // Process jobs while listening for worker termination + await Promise.race([processJobs(), catchUnload()]) + } catch (error) { + // If the worker is terminating (e.g. wall clock limit reached), + // add pending jobs to fail list with termination reason + failedJobs.push( + ...pendingJobs.map((job) => ({ + ...job, + error: error instanceof Error ? error.message : JSON.stringify(error), + })) + ) + } + + // Log completed and failed jobs for traceability + console.log('finished processing jobs:', { + completedJobs: completedJobs.length, + failedJobs: failedJobs.length, + }) + + return new Response( + JSON.stringify({ + completedJobs, + failedJobs, + }), + { + // 200 OK response + status: 200, + + // Custom headers to report job status + headers: { + 'Content-Type': 'application/json', + 'X-Completed-Jobs': completedJobs.length.toString(), + 'X-Failed-Jobs': failedJobs.length.toString(), + }, + } + ) +}) + +/** + * Generates an embedding for the given text. + */ +async function generateEmbedding(text: string) { + const response = await openai.embeddings.create({ + model: 'text-embedding-3-small', + input: text, + }) + const [data] = response.data + + if (!data) { + throw new Error('failed to generate embedding') + } + + return data.embedding +} + +/** + * Processes an embedding job. + */ +async function processJob(job: Job) { + const { jobId, id, schema, table, contentFunction, embeddingColumn } = job + + // Fetch content for the schema/table/row combination + const [row]: [Row] = await sql` + select + id, + ${sql(contentFunction)}(t) as content + from + ${sql(schema)}.${sql(table)} t + where + id = ${id} + ` + + if (!row) { + throw new Error(`row not found: ${schema}.${table}/${id}`) + } + + if (typeof row.content !== 'string') { + throw new Error(`invalid content - expected string: ${schema}.${table}/${id}`) + } + + const embedding = await generateEmbedding(row.content) + + await sql` + update + ${sql(schema)}.${sql(table)} + set + ${sql(embeddingColumn)} = ${JSON.stringify(embedding)} + where + id = ${id} + ` + + await sql` + select pgmq.delete(${QUEUE_NAME}, ${jobId}::bigint) + ` +} + +/** + * Returns a promise that rejects if the worker is terminating. + */ +function catchUnload() { + return new Promise((reject) => { + addEventListener('beforeunload', (ev: any) => { + reject(new Error(ev.detail?.reason)) + }) + }) +} +``` + +The Edge Function listens for incoming HTTP requests from `pg_net` and processes each embedding job. It is a generic worker that can handle embedding jobs for any table and column. It uses OpenAI's API to generate embeddings and updates the corresponding row in the database. It also deletes the job from the queue once it has been processed. + +The function is designed to process multiple jobs independently. If one job fails, it will not affect the processing of other jobs. The function returns a `200 OK` response with a list of completed and failed jobs. We can use this information to diagnose failed jobs. See [Troubleshooting](#troubleshooting) for more details. + +You will need to set the `OPENAI_API_KEY` environment variable to authenticate with OpenAI. When running the Edge Function locally, you can add it to a `.env` file: + +_.env_: + +``` +OPENAI_API_KEY=your-api-key +``` + +When you're ready to deploy the Edge Function, set can set the environment variable using the Supabase CLI: + +```shell +supabase secrets set --env-file .env +``` + +or + +```shell +supabase secrets set OPENAI_API_KEY= +``` + +Alternatively, you can replace the `generateEmbedding` function with your own embedding generation logic. + +See [Deploy to Production](/docs/guides/functions/deploy) for more information on how to deploy the Edge Function. + +## Usage + +Now that the infrastructure is in place, let's go through an example of how to use this system to automatically generate embeddings for a table of documents. You can use this approach with multiple tables and customize the input for each embedding generation as needed. + +### 1. Create table to store documents with embeddings + +We'll set up a new `documents` table that will store our content and embeddings: + +```sql +-- Table to store documents with embeddings +create table documents ( + id integer primary key generated always as identity, + title text not null, + content text not null, + embedding halfvec, + created_at timestamp with time zone default now() +); + +-- Index for vector search over document embeddings +create index on documents using hnsw (embedding halfvec_cosine_ops); +``` + +Our `documents` table stores the title and content of each document along with its vector embedding. We use a `halfvec` column to store the embeddings, which is a `pgvector` data type that stores float values in half precision (16 bits) to save space. + +We use an [HNSW index](/docs/guides/ai/vector-indexes/hnsw-indexes) on the vector column. Note that we are choosing `halfvec_cosine_ops` as the index method, which means our future queries will need to use cosine distance (`<=>`) to find similar embeddings. Also note that HNSW indexes support a maximum of 4000 dimensions for `halfvec` vectors, so keep this in mind when choosing an embedding model. If your model generates embeddings with more than 4000 dimensions, you will need to reduce the dimensionality before indexing them. See [Matryoshka embeddings](/blog/matryoshka-embeddings) for a potential solution to shortening dimensions. + +Also note that the table must have a primary key column named `id` for our triggers to work correctly with the `util.queue_embeddings` function and for our Edge Function to update the correct row. + +### 2. Create triggers to enqueue embedding jobs + +Now we'll set up the triggers to enqueue embedding jobs whenever content is inserted or updated: + +```sql +-- Customize the input for embedding generation +-- e.g. Concatenate title and content with a markdown header +create or replace function embedding_input(doc documents) +returns text +language plpgsql +immutable +as $$ +begin + return '# ' || doc.title || E'\n\n' || doc.content; +end; +$$; + +-- Trigger for insert events +create trigger embed_documents_on_insert + after insert + on documents + for each row + execute function util.queue_embeddings('embedding_input', 'embedding'); + +-- Trigger for update events +create trigger embed_documents_on_update + after update of title, content -- must match the columns in embedding_input() + on documents + for each row + execute function util.queue_embeddings('embedding_input', 'embedding'); +``` + +We create 2 triggers: + +1. `embed_documents_on_insert`: Enqueues embedding jobs whenever new rows are inserted into the `documents` table. + +2. `embed_documents_on_update`: Enqueues embedding jobs whenever the `title` or `content` columns are updated in the `documents` table. + +Both of these triggers use the same `util.queue_embeddings` function that will queue the embedding jobs for processing. They accept 2 arguments: + +1. `embedding_input`: The name of the function that generates the input for embedding generation. This function allows you to customize the text input passed to the embedding model (e.g. concatenating the title and content). The function should accept a single row as input and return text. + +2. `embedding`: The name of the destination column where the embedding will be stored. + +Note that the update trigger only fires when the `title` or `content` columns are updated. This is to avoid unnecessary updates to the embedding column when other columns are updated. Make sure that these columns match the columns used in the `embedding_input` function. + +{/* supa-mdx-lint-disable-next-line Rule001HeadingCase */} + +#### (Optional) Clearing embeddings on update + +Note that our trigger will enqueue new embedding jobs when content is updated, but it will not clear any existing embeddings. This means that an embedding can be temporarily out of sync with the content until the new embedding is generated and updated. + +If it is more important to have _accurate_ embeddings than _any_ embedding, you can add another trigger to clear the existing embedding until the new one is generated: + +```sql +-- Trigger to clear the embedding column on update +create trigger clear_document_embedding_on_update + before update of title, content -- must match the columns in embedding_input() + on documents + for each row + execute function util.clear_column('embedding'); +``` + +`util.clear_column` is a generic trigger function we created earlier that can be used to clear any column in a table. + +- It accepts the column name as an argument. This column must be nullable. +- It requires a `before` trigger with a `for each row` clause. +- It requires the `hstore` extension we created earlier. + +This example will clear the `embedding` column whenever the `title` or `content` columns are updated (note the `of title, content` clause). This ensures that the embedding is always in sync with the title and content, but it will result in temporary gaps in search results until the new embedding is generated. + +We intentionally use a `before` trigger because it allows us to modify the record before it's written to disk, avoiding an extra `update` statement that would be needed with an `after` trigger. + +### 3. Insert and update documents + +Let's insert a new document and update its content to see the embedding generation in action: + +```sql +-- Insert a new document +insert into documents (title, content) +values + ('Understanding Vector Databases', 'Vector databases are specialized...'); + +-- Immediately check the embedding column +select id, embedding +from documents +where title = 'Understanding Vector Databases'; +``` + +You should observe that the `embedding` column is initially `null` after inserting the document. This is because the embedding generation is asynchronous and will be processed by the Edge Function in the next scheduled task. + +Wait up to 10 seconds for the next task to run, then check the `embedding` column again: + +```sql +select id, embedding +from documents +where title = 'Understanding Vector Databases'; +``` + +You should see the generated embedding for the document. + +Next let's update the content of the document: + +```sql +-- Update the content of the document +update documents +set content = 'Vector databases allow you to query...' +where title = 'Understanding Vector Databases'; + +-- Immediately check the embedding column +select id, embedding +from documents +where title = 'Understanding Vector Databases'; +``` + +You should observe that the `embedding` column is reset to `null` after updating the content. This is because of the trigger we added to clear existing embeddings whenever the content is updated. The embedding will be regenerated by the Edge Function in the next scheduled task. + +Wait up to 10 seconds for the next task to run, then check the `embedding` column again: + +```sql +select id, embedding +from documents +where title = 'Understanding Vector Databases'; +``` + +You should see the updated embedding for the document. + +Finally we'll update the title of the document: + +```sql +-- Update the title of the document +update documents +set title = 'Understanding Vector Databases with Supabase' +where title = 'Understanding Vector Databases'; +``` + +You should observe that the `embedding` column is once again reset to `null` after updating the title. This is because the trigger we added to clear existing embeddings fires when either the `content` or `title` columns are updated. The embedding will be regenerated by the Edge Function in the next scheduled task. + +Wait up to 10 seconds for the next task to run, then check the `embedding` column again: + +```sql +select id, embedding +from documents +where title = 'Understanding Vector Databases with Supabase'; +``` + +You should see the updated embedding for the document. + +## Troubleshooting + +The `embed` Edge Function processes a batch of embedding jobs and returns a `200 OK` response with a list of completed and failed jobs in the body. For example: + +```json +{ + "completedJobs": [ + { + "jobId": "1", + "id": "1", + "schema": "public", + "table": "documents", + "contentFunction": "embedding_input", + "embeddingColumn": "embedding" + } + ], + "failedJobs": [ + { + "jobId": "2", + "id": "2", + "schema": "public", + "table": "documents", + "contentFunction": "embedding_input", + "embeddingColumn": "embedding", + "error": "error connecting to openai api" + } + ] +} +``` + +It also returns the number of completed and failed jobs in the response headers. For example: + +``` +X-Completed-Jobs: 1 +X-Failed-Jobs: 1 +``` + +You can also use the `X-Deno-Execution-Id` header to trace the execution of the Edge Function within the [dashboard](/dashboard/project/_/functions) logs. + +Each failed job includes an `error` field with a description of the failure. Reasons for a job failing could include: + +- An error generating the embedding via external API +- An error connecting to the database +- The edge function being terminated (e.g. due to a wall clock limit) +- Any other error thrown during processing + +`pg_net` stores HTTP responses in the `net._http_response` table, which can be queried to diagnose issues with the embedding generation process. + +```sql +select + * +from + net._http_response +where + (headers->>'X-Failed-Jobs')::int > 0; +``` + +## Conclusion + +Automating embedding generation and updates in Postgres allow you to build powerful semantic search capabilities without the complexity of managing embeddings manually. + +By combining Postgres features like triggers, queues, and other extensions with Supabase Edge Functions, we can create a robust system that handles embedding generation asynchronously and retries failed jobs automatically. + +This system can be customized to work with any content and embedding generation service, providing a flexible and scalable solution for semantic search in Postgres. + +## See also + +- [What are embeddings?](/docs/guides/ai/concepts) +- [Semantic search](/docs/guides/ai/semantic-search) +- [Vector indexes](/docs/guides/ai/vector-indexes) +- [Supabase Edge Functions](/docs/guides/functions) diff --git a/apps/docs/content/guides/database/prisma.mdx b/apps/docs/content/guides/database/prisma.mdx index 737ce4f6e01..dbb1606d7d3 100644 --- a/apps/docs/content/guides/database/prisma.mdx +++ b/apps/docs/content/guides/database/prisma.mdx @@ -98,11 +98,11 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t ```bash yarn init -y - yarn install prisma typescript ts-node @types/node --save-dev + yarn add prisma typescript ts-node @types/node --save-dev - yarn dlx tsc --init + npx tsc --init - yarn dlx prisma init + npx prisma init ``` @@ -241,7 +241,7 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t ```bash - yarn dlx prisma migrate dev --name first_prisma_migration + npx prisma migrate dev --name first_prisma_migration ``` @@ -318,7 +318,7 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t ```bash - yarn dlx prisma db pull + npx prisma db pull ``` Create a migration file @@ -328,7 +328,7 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t Synchronize the migrations ```bash - yarn dlx prisma migrate diff \ + npx prisma migrate diff \ --from-empty \ --to-schema-datamodel prisma/schema.prisma \ --script > prisma/migrations/0_init_supabase/migration.sql @@ -338,7 +338,7 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t ```bash - yarn dlx prisma migrate resolve --applied 0_init_supabase + npx prisma migrate resolve --applied 0_init_supabase ``` @@ -403,8 +403,8 @@ If you plan to solely use Prisma instead of the Supabase Data API (PostgREST), t ```sh - yarn install @prisma/client - yarn dlx prisma generate + yarn add @prisma/client + npx prisma generate ``` diff --git a/apps/docs/spec/cli_v1_commands.yaml b/apps/docs/spec/cli_v1_commands.yaml index c0f2c25f8da..63e8b0ed8e5 100644 --- a/apps/docs/spec/cli_v1_commands.yaml +++ b/apps/docs/spec/cli_v1_commands.yaml @@ -3006,7 +3006,7 @@ commands: Linked project is up to date. - id: self-hosted name: Self hosted - code: supabase db push --db-url "postgres://user:pass@127.0.0.1:5432/postgres" + code: supabase db push --db-url "postgres://user.tenant:pass@127.0.0.1:5432" response: | Pushing migration 20230410135622_create_employees_table.sql... Finished supabase db push. diff --git a/apps/docs/spec/supabase_kt_v3.yml b/apps/docs/spec/supabase_kt_v3.yml index b375a697e46..970fc1229bb 100644 --- a/apps/docs/spec/supabase_kt_v3.yml +++ b/apps/docs/spec/supabase_kt_v3.yml @@ -2883,7 +2883,7 @@ functions: isSpotlight: true code: | ```kotlin - val supabase = createSupabaseClient(supabaseURL = "https://xyzcompany.supabase.co'", supabaseKey = "public-anon-key") { ... } + val supabase = createSupabaseClient(supabaseUrl = "https://xyzcompany.supabase.co'", supabaseKey = "public-anon-key") { ... } val auth = supabase.auth ``` - id: sign-up diff --git a/apps/studio/components/interfaces/Auth/Users/DeleteUserModal.tsx b/apps/studio/components/interfaces/Auth/Users/DeleteUserModal.tsx new file mode 100644 index 00000000000..ff513fb397f --- /dev/null +++ b/apps/studio/components/interfaces/Auth/Users/DeleteUserModal.tsx @@ -0,0 +1,61 @@ +import { useParams } from 'common' +import { toast } from 'sonner' + +import { useUserDeleteMutation } from 'data/auth/user-delete-mutation' +import { User } from 'data/auth/users-infinite-query' +import { timeout } from 'lib/helpers' +import ConfirmationModal from 'ui-patterns/Dialogs/ConfirmationModal' + +interface DeleteUserModalProps { + visible: boolean + selectedUser?: User + onClose: () => void + onDeleteSuccess?: () => void +} + +export const DeleteUserModal = ({ + visible, + selectedUser, + onClose, + onDeleteSuccess, +}: DeleteUserModalProps) => { + const { ref: projectRef } = useParams() + + const { mutate: deleteUser, isLoading: isDeleting } = useUserDeleteMutation({ + onSuccess: () => { + toast.success(`Successfully deleted ${selectedUser?.email}`) + onDeleteSuccess?.() + }, + }) + + const handleDeleteUser = async () => { + await timeout(200) + if (!projectRef) return console.error('Project ref is required') + if (selectedUser?.id === undefined) { + return toast.error(`Failed to delete user: User ID not found`) + } + deleteUser({ projectRef, userId: selectedUser.id }) + } + + return ( + onClose()} + onConfirm={() => handleDeleteUser()} + alert={{ + title: 'Deleting a user is irreversible', + description: + 'This will remove the selected the user from the project and all associated data.', + }} + > +

+ This is permanent! Are you sure you want to delete the user{' '} + {selectedUser?.email ?? selectedUser?.phone ?? 'this user'}? +

+ + ) +} diff --git a/apps/studio/components/interfaces/Auth/Users/UserOverview.tsx b/apps/studio/components/interfaces/Auth/Users/UserOverview.tsx index 958d95fe0c3..d8807b64234 100644 --- a/apps/studio/components/interfaces/Auth/Users/UserOverview.tsx +++ b/apps/studio/components/interfaces/Auth/Users/UserOverview.tsx @@ -10,7 +10,6 @@ import { ButtonTooltip } from 'components/ui/ButtonTooltip' import CopyButton from 'components/ui/CopyButton' import { useAuthConfigQuery } from 'data/auth/auth-config-query' import { useUserDeleteMFAFactorsMutation } from 'data/auth/user-delete-mfa-factors-mutation' -import { useUserDeleteMutation } from 'data/auth/user-delete-mutation' import { useUserResetPasswordMutation } from 'data/auth/user-reset-password-mutation' import { useUserSendMagicLinkMutation } from 'data/auth/user-send-magic-link-mutation' import { useUserSendOTPMutation } from 'data/auth/user-send-otp-mutation' @@ -24,6 +23,7 @@ import { Admonition } from 'ui-patterns/admonition' import ConfirmationModal from 'ui-patterns/Dialogs/ConfirmationModal' import { PROVIDERS_SCHEMAS } from '../AuthProvidersFormValidation' import { BanUserModal } from './BanUserModal' +import { DeleteUserModal } from './DeleteUserModal' import { UserHeader } from './UserHeader' import { PANEL_PADDING } from './UserPanel' import { providerIconMap } from './Users.utils' @@ -109,13 +109,6 @@ export const UserOverview = ({ user, onDeleteSuccess }: UserOverviewProps) => { toast.error(`Failed to send OTP: ${err.message}`) }, }) - const { mutate: deleteUser } = useUserDeleteMutation({ - onSuccess: () => { - toast.success(`Successfully deleted ${user?.email}`) - setIsDeleteModalOpen(false) - onDeleteSuccess() - }, - }) const { mutate: deleteUserMFAFactors } = useUserDeleteMFAFactorsMutation({ onSuccess: () => { toast.success("Successfully deleted the user's factors") @@ -129,15 +122,6 @@ export const UserOverview = ({ user, onDeleteSuccess }: UserOverviewProps) => { }, }) - const handleDelete = async () => { - await timeout(200) - if (!projectRef) return console.error('Project ref is required') - if (user.id === undefined) { - return toast.error(`Failed to delete user: User ID not found`) - } - deleteUser({ projectRef, userId: user.id }) - } - const handleDeleteFactors = async () => { await timeout(200) if (!projectRef) return console.error('Project ref is required') @@ -179,7 +163,7 @@ export const UserOverview = ({ user, onDeleteSuccess }: UserOverviewProps) => { )} -
+
{
- setIsDeleteModalOpen(false)} - onConfirm={() => handleDelete()} - alert={{ - title: 'Deleting a user is irreversible', - description: 'This will remove the user from the project and all associated data.', + selectedUser={user} + onClose={() => setIsDeleteModalOpen(false)} + onDeleteSuccess={() => { + setIsDeleteModalOpen(false) + onDeleteSuccess() }} - > -

- This is permanent! Are you sure you want to delete the user{' '} - {user.email ?? user.phone ?? 'this user'}? -

- + />
-

{property}

+

{property}

{typeof value === 'boolean' ? (
{value ? ( @@ -481,7 +457,7 @@ export const RowData = ({ property, value }: { property: string; value?: string
) : (
-

{!value ? '-' : value}

+

{!value ? '-' : value}

{!!value && ( void + onSelectDeleteUser: (user: User) => void }) => { const columnOrder = config.map((c) => c.id) ?? USERS_TABLE_COLUMNS.map((c) => c.id) @@ -319,42 +330,70 @@ export const formatUserColumns = ({ } return ( -
- {/* [Joshen] Not convinced this is the ideal way to display the icons, but for now */} - {col.id === 'providers' && - row.provider_icons.map((icon: string, idx: number) => { - const provider = row.providers[idx] - return ( -
- {`${provider} -
- ) - })} - {col.id === 'last_sign_in_at' && !isConfirmed ? ( -

Waiting for verification

- ) : ( -

- {formattedValue === null ? '-' : formattedValue} -

- )} -
+ + +
+ {/* [Joshen] Not convinced this is the ideal way to display the icons, but for now */} + {col.id === 'providers' && + row.provider_icons.map((icon: string, idx: number) => { + const provider = row.providers[idx] + return ( +
+ {`${provider} +
+ ) + })} + {col.id === 'last_sign_in_at' && !isConfirmed ? ( +

Waiting for verification

+ ) : ( +

+ {formattedValue === null ? '-' : formattedValue} +

+ )} +
+ + e.stopPropagation()}> + e.stopPropagation()} + onSelect={() => { + const value = col.id === 'providers' ? row.providers.join(', ') : formattedValue + copyToClipboard(value) + }} + > + + Copy {col.id === 'id' ? col.name : col.name.toLowerCase()} + + + e.stopPropagation()} + onSelect={() => { + if (user) onSelectDeleteUser(user) + }} + > + + Delete user + + + ) }, } diff --git a/apps/studio/components/interfaces/Auth/Users/UsersV2.tsx b/apps/studio/components/interfaces/Auth/Users/UsersV2.tsx index f8dfb7a3afd..dca0bf82095 100644 --- a/apps/studio/components/interfaces/Auth/Users/UsersV2.tsx +++ b/apps/studio/components/interfaces/Auth/Users/UsersV2.tsx @@ -16,7 +16,7 @@ import { FormHeader } from 'components/ui/Forms/FormHeader' import { authKeys } from 'data/auth/keys' import { useUserDeleteMutation } from 'data/auth/user-delete-mutation' import { useUsersCountQuery } from 'data/auth/users-count-query' -import { useUsersInfiniteQuery } from 'data/auth/users-infinite-query' +import { User, useUsersInfiniteQuery } from 'data/auth/users-infinite-query' import { useLocalStorageQuery } from 'hooks/misc/useLocalStorage' import { LOCAL_STORAGE_KEYS } from 'lib/constants' import { @@ -44,6 +44,7 @@ import { Input } from 'ui-patterns/DataInputs/Input' import ConfirmationModal from 'ui-patterns/Dialogs/ConfirmationModal' import { GenericSkeletonLoader } from 'ui-patterns/ShimmeringLoader' import AddUserDropdown from './AddUserDropdown' +import { DeleteUserModal } from './DeleteUserModal' import { UserPanel } from './UserPanel' import { MAX_BULK_DELETE, PROVIDER_FILTER_OPTIONS } from './Users.constants' import { formatUserColumns, formatUsersData, isAtBottom } from './Users.utils' @@ -83,13 +84,16 @@ export const UsersV2 = () => { const [search, setSearch] = useState('') const [filter, setFilter] = useState('all') const [filterKeywords, setFilterKeywords] = useState('') - const [selectedUsers, setSelectedUsers] = useState>(new Set([])) const [selectedColumns, setSelectedColumns] = useState([]) const [selectedProviders, setSelectedProviders] = useState([]) - const [selectedUser, setSelectedUser] = useState() const [sortByValue, setSortByValue] = useState('created_at:desc') + + const [selectedUser, setSelectedUser] = useState() + const [selectedUsers, setSelectedUsers] = useState>(new Set([])) + const [selectedUserToDelete, setSelectedUserToDelete] = useState() const [showDeleteModal, setShowDeleteModal] = useState(false) const [isDeletingUsers, setIsDeletingUsers] = useState(false) + const [ columnConfiguration, setColumnConfiguration, @@ -143,7 +147,7 @@ export const UsersV2 = () => { const totalUsers = countData ?? 0 const users = useMemo(() => data?.pages.flatMap((page) => page.result) ?? [], [data?.pages]) // [Joshen] Only relevant for when selecting one user only - const selectedUserToDelete = users.find((u) => u.id === [...selectedUsers][0]) + const selectedUserFromCheckbox = users.find((u) => u.id === [...selectedUsers][0]) const handleScroll = (event: UIEvent) => { const isScrollingHorizontally = xScroll.current !== event.currentTarget.scrollLeft @@ -199,6 +203,11 @@ export const UsersV2 = () => { 500 ) + const onSelectDeleteUser = (user: User) => { + setSelectedUsers(new Set([user.id])) + setShowDeleteModal(true) + } + const handleDeleteUsers = async () => { if (!projectRef) return console.error('Project ref is required') const userIds = [...selectedUsers] @@ -237,6 +246,7 @@ export const UsersV2 = () => { users: users ?? [], visibleColumns: selectedColumns, setSortByValue, + onSelectDeleteUser, }) setColumns(columns) if (columns.length < USERS_TABLE_COLUMNS.length) { @@ -377,6 +387,7 @@ export const UsersV2 = () => { users: users ?? [], visibleColumns: value, setSortByValue, + onSelectDeleteUser, }) setSelectedColumns(value) @@ -580,12 +591,20 @@ export const UsersV2 = () => { {selectedUsers.size === 1 ? ( {' '} - {selectedUserToDelete?.email ?? selectedUserToDelete?.phone ?? 'this user'} + {selectedUserFromCheckbox?.email ?? selectedUserFromCheckbox?.phone ?? 'this user'} ) : null} ?

+ + {/* [Joshen] For deleting via context menu, the dialog above is dependent on the selectedUsers state */} + setSelectedUserToDelete(undefined)} + onDeleteSuccess={() => setSelectedUserToDelete(undefined)} + /> ) } diff --git a/apps/www/_blog/2024-08-12-github-copilot-extension-for-vs-code.mdx b/apps/www/_blog/2024-08-12-github-copilot-extension-for-vs-code.mdx index 9cd05fe0e1e..a69492142f8 100644 --- a/apps/www/_blog/2024-08-12-github-copilot-extension-for-vs-code.mdx +++ b/apps/www/_blog/2024-08-12-github-copilot-extension-for-vs-code.mdx @@ -64,7 +64,7 @@ List the Storage buckets in your Supabase project. We're excited to continue adding more features that will make your development experience with Supabase even more delightful - and for this we need your help! If you have any feedback, feature requests, or bug reports, please [open an issue on GitHub](https://github.com/supabase-community/supabase-vscode-extension/issues). -The extension requires you to have the Supabase CLI installed and have your project running locally. In a future release, we will integrate the [Supabase Managamenet API](/docs/reference/api/introduction) into the extension to make connecting to your hosted Supabase projects as seamless as possible. +The extension requires you to have the Supabase CLI installed and have your project running locally. In a future release, we will integrate the [Supabase Management API](/docs/reference/api/introduction) into the extension to make connecting to your hosted Supabase projects as seamless as possible. ## Contributing to Supabase diff --git a/apps/www/_blog/2024-08-13-supabase-realtime-broadcast-and-presence-authorization.mdx b/apps/www/_blog/2024-08-13-supabase-realtime-broadcast-and-presence-authorization.mdx index 15999b61864..8e70366f9c5 100644 --- a/apps/www/_blog/2024-08-13-supabase-realtime-broadcast-and-presence-authorization.mdx +++ b/apps/www/_blog/2024-08-13-supabase-realtime-broadcast-and-presence-authorization.mdx @@ -212,7 +212,7 @@ Realtime uses the private flag client's define when creating channel, takes the light: '/images/blog/2024-08-13-supabase-realtime-broadcast-and-presence-authorization/one-user-connection--light.png', }} - alt="Flow of checks done against the databse to determine the policies for a user connection." + alt="Flow of checks done against the database to determine the policies for a user connection." /> ## How is this approach performant? diff --git a/apps/www/_blog/2024-12-06-launch-week-13-top-10.mdx b/apps/www/_blog/2024-12-06-launch-week-13-top-10.mdx index 098653eff97..51281ddcf66 100644 --- a/apps/www/_blog/2024-12-06-launch-week-13-top-10.mdx +++ b/apps/www/_blog/2024-12-06-launch-week-13-top-10.mdx @@ -35,7 +35,7 @@ A feature tri-fecta: Edge Functions now support Websockets for things like OpenA ## #4: CLI v2: Config as Code -We realeased v2 of the CLI, adding support for Configuration as Code. You can now use the CLI in your GitHub actions to keep all of your project configuration in sync. +We released v2 of the CLI, adding support for Configuration as Code. You can now use the CLI in your GitHub actions to keep all of your project configuration in sync. ## #5: High Performance Disks diff --git a/supa-mdx-lint/Rule003Spelling.toml b/supa-mdx-lint/Rule003Spelling.toml index 2e663020e6f..5f2916dce40 100644 --- a/supa-mdx-lint/Rule003Spelling.toml +++ b/supa-mdx-lint/Rule003Spelling.toml @@ -42,6 +42,7 @@ allow_list = [ "[Dd]evs?", "[Dd]iff(s|ing|ed)?", "[Dd]ropdown", + "[Ee]nqueues?", "[Ee]nums?", "[Ee]nv", "[Ff]atals", @@ -54,6 +55,7 @@ allow_list = [ "[Hh]ypertables?", "[KMG]bps", "[KMG]iB", + "[Mm]atryoshka", "[Mm]essageBird", "[Mm]icroservices?", "[Mm]iddlewares?",