From 78d0755008e77745c2cac3a79d64d5b1318ab90d Mon Sep 17 00:00:00 2001 From: Charis <26616127+charislam@users.noreply.github.com> Date: Tue, 26 Nov 2024 14:28:40 -0500 Subject: [PATCH] docs(ci): expand linter scope (#30678) Expand linter scope to cover `ai` directory as well. --- .github/workflows/docs-lint-v2.yml | 6 +++--- .../semantic-image-search-amazon-titan.mdx | 2 +- .../guides/ai/integrations/amazon-bedrock.mdx | 8 ++++---- supa-mdx-lint.config.toml | 17 +++++++++++++++-- 4 files changed, 23 insertions(+), 10 deletions(-) diff --git a/.github/workflows/docs-lint-v2.yml b/.github/workflows/docs-lint-v2.yml index 31cfe6ea4fd..1536658780f 100644 --- a/.github/workflows/docs-lint-v2.yml +++ b/.github/workflows/docs-lint-v2.yml @@ -28,10 +28,10 @@ jobs: ~/.cargo/registry/index/ ~/.cargo/registry/cache/ ~/.cargo/git/db/ - key: 9fd8c8fa7487a3d454a676e6e3d7409af34fc715 + key: e23c860111349d8bac17b78b1fe632afe84223f9 - name: install linter if: steps.cache-cargo.outputs.cache-hit != 'true' - run: cargo install --locked --git https://github.com/supabase-community/supa-mdx-lint --rev 9fd8c8fa7487a3d454a676e6e3d7409af34fc715 + run: cargo install --locked --git https://github.com/supabase-community/supa-mdx-lint --rev e23c860111349d8bac17b78b1fe632afe84223f9 - name: install reviewdog uses: reviewdog/action-setup@3f401fe1d58fe77e10d665ab713057375e39b887 # v1.3.0 with: @@ -41,4 +41,4 @@ jobs: REVIEWDOG_GITHUB_API_TOKEN: ${{ secrets.GITHUB_TOKEN }} run: | set -o pipefail - supa-mdx-lint apps/docs/content/guides/getting-started --format rdf | reviewdog -f=rdjsonl -reporter=github-pr-review + supa-mdx-lint apps/docs/content/guides/getting-started apps/docs/content/guides/ai --format rdf | reviewdog -f=rdjsonl -reporter=github-pr-review diff --git a/apps/docs/content/guides/ai/examples/semantic-image-search-amazon-titan.mdx b/apps/docs/content/guides/ai/examples/semantic-image-search-amazon-titan.mdx index c2dd616366e..373720b7797 100644 --- a/apps/docs/content/guides/ai/examples/semantic-image-search-amazon-titan.mdx +++ b/apps/docs/content/guides/ai/examples/semantic-image-search-amazon-titan.mdx @@ -28,7 +28,7 @@ Then initialize a new project: poetry new aws_bedrock_image_search ``` -## Spin up a Postgres Database with pgvector +## Spin up a Postgres database with pgvector If you haven't already, head over to [database.new](https://database.new) and create a new project. Every Supabase project comes with a full Postgres database and the [pgvector extension](/docs/guides/database/extensions/pgvector) preconfigured. diff --git a/apps/docs/content/guides/ai/integrations/amazon-bedrock.mdx b/apps/docs/content/guides/ai/integrations/amazon-bedrock.mdx index d18f9a6bc83..02699d3271d 100644 --- a/apps/docs/content/guides/ai/integrations/amazon-bedrock.mdx +++ b/apps/docs/content/guides/ai/integrations/amazon-bedrock.mdx @@ -10,7 +10,7 @@ tocVideo: 'A3uND5sgiO0' This guide will walk you through an example using Amazon Bedrock SDK with `vecs`. We will create embeddings using the Amazon Titan Embeddings G1 – Text v1.2 (amazon.titan-embed-text-v1) model, insert these embeddings into a PostgreSQL database using vecs, and then query the collection to find the most similar sentences to a given query sentence. -## Create an Environment +## Create an environment First, you need to set up your environment. You will need Python 3.7+ with the `vecs` and `boto3` libraries installed. @@ -25,7 +25,7 @@ You'll also need: - [Credentials to your AWS account](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html) - [A Postgres Database with the pgvector extension](hosting.md) -## Create Embeddings +## Create embeddings Next, we will use Amazon’s Titan Embedding G1 - Text v1.2 model to create embeddings for a set of sentences. @@ -67,7 +67,7 @@ for sentence in dataset: ``` -### Store the Embeddings with vecs +### Store the embeddings with vecs Now that we have our embeddings, we can insert them into a PostgreSQL database using vecs. @@ -90,7 +90,7 @@ sentences.upsert(records=embeddings) sentences.create_index() ``` -### Querying for Most Similar Sentences +### Querying for most similar sentences Now, we query the `sentences` collection to find the most similar sentences to a sample query sentence. First need to create an embedding for the query sentence. Next, we query the collection we created earlier to find the most similar sentences. diff --git a/supa-mdx-lint.config.toml b/supa-mdx-lint.config.toml index 1eba0db28cc..745fe591233 100644 --- a/supa-mdx-lint.config.toml +++ b/supa-mdx-lint.config.toml @@ -5,32 +5,42 @@ ignore_patterns = ["**/_*.mdx"] # Words that may be uppercased even if they are not the first word in the sentence. # Can also specify a regex that is compatible with the [Rust regex crate](https://docs.rs/regex/latest/regex/). may_uppercase = [ - "[A-Z]{3,5}", + "[A-Z0-9]{2,5}", "Android", "Angular", "Apple", "Auth", + "ChatGPT", "Content Delivery Network", "Dart", - "Edge Functions", + "Edge Functions?", "Flutter", "GoTrue", "Google", "GraphQL", + "Hugging Face", + "I", + "IVFFlat", "Ionic Angular", "Ionic React", "Ionic Vue", "JavaScript", "Kotlin", + "Navigable Small World", "Next.js", "Nuxt", "OpenAI", + "Poetry", "Postgres", "PostgreSQL", "PostgREST", + "Python", "React", "React Native", + "Reciprocal Ranked Fusion", "RedwoodJS", + "Retrieval Plugin", + "Roboflow Inference", "Row Level Security", "Server-Side Auth", "Single Sign-On", @@ -40,8 +50,11 @@ may_uppercase = [ "SvelteKit", "Swift", "SwiftUI", + "TypeScript", "Xcode", + "Vecs", "Vue", + "Wrappers", ] # Words that may be lowercased even if they are the first word in the sentence. # Can also specify a regex that is compatible with the [Rust regex crate](https://docs.rs/regex/latest/regex/).