Merge branch 'develop' into 'fb-LEAP-1292'

Workflow run: https://github.com/HumanSignal/label-studio/actions/runs/13567909568

Author: triklozoid

.github/workflows/follow-merge-upstream-repo-sync-v2.yml

@@ -17,16 +17,12 @@ concurrency:
   group: ${{ github.workflow }}-${{ inputs.branch_name }}
   cancel-in-progress: true
 
-env:
-  NODE: "18"
-  YARN: "1.22"
-
 jobs:
   sync:
     name: Sync PR
     runs-on: ubuntu-latest
     outputs:
-      label-studio-sdk: "${{ steps.upstream-prs.outputs.label-studio-sdk }}"
+      label-studio-sdk: "${{ fromJSON(steps.upstream-prs.outputs.shas).label-studio-sdk }}"
     steps:
       - uses: hmarr/debug-action@v3.0.0
 
@@ -69,109 +65,18 @@ jobs:
           path: ./.github/actions-hub
 
       - name: Get Upstream PRs
+        uses: ./.github/actions-hub/actions/follow-merge-upstream-prs
         id: upstream-prs
-        uses: actions/github-script@v7
-        env:
-          BRANCH_NAME: ${{ inputs.branch_name }}
         with:
-          github-token: ${{ secrets.GIT_PAT }}
-          script: |
-            const { repo, owner } = context.repo;
-            const branch_name = process.env.BRANCH_NAME;
-            const pyProjectPath = "pyproject.toml";
-            const repos = ["label-studio-sdk"];
-            const repos_infra = [];
-            const base_branch_name = 'develop';
-            
-            let shas = {};
-
-            // GET UPSTREAM PRS
-            let upstream_pulls = [];
-            for (const repo of repos.concat(repos_infra)) {
-              const {data: pulls} = await github.rest.pulls.list({
-                owner,
-                repo,
-                state: "all",
-                head: `${owner}:${branch_name}`,
-              });
-              const first_open_pull = pulls.find(e => e.state === 'open');
-              const pull = first_open_pull || pulls[0];
-              if (pull) {
-                core.info(`PRs found for ${repo} ${pull.html_url} ${pull.merged_at ? 'merged' : pull.state} ${pull.merged_at ? pull.merge_commit_sha : pull.head.sha}`)
-                upstream_pulls.push(pull);
-                if (pull.merged_at) {
-                  shas[repo] = pull.merge_commit_sha;
-                } else if (pull.state === 'open') {
-                  shas[repo] = pull.head.sha;
-                }
-              } else {
-                core.notice(`No open upstream PRs found for ${repo}`)
-              }
-            }
-            
-            // GET BASE VERSIONS
-            const {data: pyprojectBlob} = await github.rest.repos.getContent({
-              owner: owner,
-              repo: repo,
-              ref: base_branch_name,
-              path: pyProjectPath,
-            });
-            const base_pyproject = Buffer.from(pyprojectBlob.content, pyprojectBlob.encoding).toString("utf8");
-            for (const repo of repos) {
-              const match = base_pyproject.match(new RegExp(`${repo}\/archive.*(?<sha>[a-f0-9]{40})`));
-              if (match && match.groups.sha) {
-                core.info(`Base version for ${repo} ${pyprojectBlob.html_url} ${match.groups.sha}`);
-                shas[repo] = shas[repo] || match.groups.sha;
-              } else {
-                core.setFailed(`Could not parse ${repo} version from ${pyprojectBlob.html_url}`);
-              }
-            }
-            
-            for (const [key, value] of Object.entries(shas)) {
-              core.setOutput(key, value);
-            }
-            
-            core.info(`Base branch name ${base_branch_name}`);
-            core.setOutput('base_branch_name', base_branch_name);
-            
-            if (upstream_pulls.length > 0) {
-              core.info(`Title ${upstream_pulls[0].title}`);
-              core.setOutput('title', upstream_pulls[0].title);
-            }
-            
-            const upstream_prs_urls = upstream_pulls.map(e => e.html_url).join(',');
-            core.info(`Upstream PRs URLs ${upstream_prs_urls}`);
-            core.setOutput('upstream_prs_urls', upstream_prs_urls);
-            
-            let assignees = [];
-            for (const pull of upstream_pulls) {
-              if (pull.user) assignees.push(pull.user.login);
-              if (pull.assignee) assignees.push(pull.assignee.login);
-              assignees.concat(pull.assignees.map(e => e.name));
-            }
-            assignees = assignees.filter(x => x !== 'robot-ci-heartex');
-            core.info(`Assignees ${assignees.join(',')}`);
-            core.setOutput('assignees', assignees.join(','));
-            
-            if (assignees.length > 0) {
-              const author_username = assignees[0];
-              core.info(`Author username ${author_username}`);
-              core.setOutput('author_username', author_username);
-            }
-            
-            let status = "open"
-            if (upstream_pulls.every(p => p.merged_at)) {
-              status = 'merged';
-            } else if (upstream_pulls.every(p => p.closed_at)) {
-              status = 'closed';
-            }
-            core.info(`Status: ${status}`);
-            core.setOutput("status", status);
+          branch_name: "${{ inputs.branch_name }}"
+          poetry_repositories: "label-studio-sdk"
+          infra_repositories: ""
+          github_token: "${{ secrets.GIT_PAT }}"
 
       - name: Git Configure
         uses: ./.github/actions-hub/actions/git-configure
         with:
-          username: ${{ steps.upstream-prs.outputs.author_username }}
+          username: ${{ github.event.client_payload.actor || steps.upstream-prs.outputs.author_username }}
 
       - name: Git Merge
         id: merge
@@ -197,12 +102,12 @@ jobs:
       - name: Commit submodule
         shell: bash
         env:
-          SDK_SHA: "${{ steps.upstream-prs.outputs.label-studio-sdk }}"
+          SDK_SHA: "${{ fromJSON(steps.upstream-prs.outputs.shas).label-studio-sdk }}"
           COMMIT_MESSAGE: "Sync Follow Merge dependencies"
           COMMIT_MESSAGE_WORKFLOW_LINK: "Workflow run: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"
         run: |
           set -xeuo pipefail
-                    
+          
           if [[ -n "${SDK_SHA}" ]]; then
             poetry add "https://github.com/HumanSignal/label-studio-sdk/archive/${SDK_SHA}.zip" --lock
           fi
@@ -223,6 +128,7 @@ jobs:
         with:
           github_token: ${{ secrets.GIT_PAT }}
           branch_name: "${{ steps.get-branch.outputs.branch_name }}"
+          base_branch_name: "${{ steps.upstream-prs.outputs.base_branch_name }}"
           title: "${{ steps.upstream-prs.outputs.title }}"
           upstream_prs_urls: "${{ steps.upstream-prs.outputs.upstream_prs_urls }}"
 
@@ -235,6 +141,30 @@ jobs:
           pullrequest_number: "${{ steps.get-pr.outputs.number }}"
           assignees: "${{ steps.upstream-prs.outputs.assignees }}"
 
+      - name: Add PR state Labels
+        if: steps.upstream-prs.outputs.status == 'stale'
+        uses: ./.github/actions-hub/actions/github-add-pull-request-labels
+        continue-on-error: true
+        with:
+          github_token: ${{ secrets.GIT_PAT }}
+          pullrequest_number: "${{ steps.get-pr.outputs.number }}"
+          labels: "FM Stale"
+
+      - name: Merge Stale PR (Dry run)
+        if: steps.upstream-prs.outputs.status == 'stale'
+        continue-on-error: true
+        shell: bash
+        env:
+          GIT_PAT: ${{ secrets.GIT_PAT }}
+          BRANCH_NAME: "origin/${{ steps.get-branch.outputs.branch_name }}"
+          BASE_BRANCH_NAME: "origin/${{ steps.upstream-prs.outputs.base_branch_name }}"
+        run: |
+          if git diff --quiet "${BASE_BRANCH_NAME}..${BRANCH_NAME}"; then
+            echo "No changes detected."
+          else
+            echo "Changes detected in PR."
+          fi
+
       - name: Convert to ready for review
         if: steps.upstream-prs.outputs.status == 'merged'
         id: ready-for-review-pr

Dockerfile

@@ -87,9 +87,17 @@ ENV PATH="$VENV_PATH/bin:$PATH"
 # Copy dependency files
 COPY pyproject.toml poetry.lock README.md ./
 
+# Set a default build argument for including dev dependencies
+ARG INCLUDE_DEV=false
+
 # Install dependencies without dev packages
 RUN --mount=type=cache,target=$POETRY_CACHE_DIR,sharing=locked \
-    poetry check --lock && poetry install --no-root --without test --extras uwsgi
+    poetry check --lock && \
+    if [ "$INCLUDE_DEV" = "true" ]; then \
+        poetry install --no-root --extras uwsgi --with test; \
+    else \
+        poetry install --no-root --without test --extras uwsgi; \
+    fi
 
 # Install LS
 COPY label_studio label_studio

docker-compose.override.example.yml

@@ -1,5 +1,13 @@
 version: "3.9"
 services:
   app:
+    build:
+      args:
+        - INCLUDE_DEV=true
     env_file:
       - .env
+
+  nginx:
+    build:
+      args:
+        - INCLUDE_DEV=true

docs/source/guide/ask_ai.md

@@ -1,19 +1,19 @@
 ---
-title: About Ask AI - Beta 🧪
-short: Ask AI
+title: About AI Features - Beta 🧪
+short: AI features
 tier: enterprise
 type: guide
 order: 0
 order_enterprise: 356
-meta_title: About Ask AI 
-meta_description: Information about using the Ask AI tool in Label Studio
+meta_title: About AI features 
+meta_description: Information about using the AI features in Label Studio
 section: "Manage Your Organization"
 date: 2025-01-28 16:40:16
 ---
 
-The Ask AI tool is an LLM that has been trained on our documentation, codebase, and several other Label Studio resources. 
+AI features in Label Studio use an LLM that has been trained on our documentation, codebase, and several other Label Studio resources. 
 
-You can use Ask AI to create or refine your labeling configuration. Instead of manually building labeling interfaces or project instructions from scratch, you can prompt the AI with a description of what your labeling project needs, and the AI generates a suggested configuration. 
+You can use AI to create or refine your labeling configuration. Instead of manually building labeling interfaces or project instructions from scratch, you can prompt the AI with a description of what your labeling project needs, and the AI generates a suggested configuration. 
 
 
 ## What models do you use?
@@ -36,13 +36,13 @@ The model is trained on public resources like our documentation, codebase, blog,
 
 We are on a Tier 5 OpenAI account, and opt out of all requests for training data.
 
-We track requests to Ask AI to use as quality control, but they are only used to test the outputs of the model.  For example: If Company X asks "Make a project to label opossums," we may notice that Ask AI did not provide a satisfactory answer and we may create configurations with opossums in them and train the model on them. The model would not be trained on any of Company X's questions or data.
+We track requests to our AI to use as quality control, but they are only used to test the outputs of the model.  For example: If Company X asks "Make a project to label opossums," we may notice that our AI did not provide a satisfactory answer and we may create configurations with opossums in them and train the model on them. The model would not be trained on any of Company X's questions or data.
 
 All tracked data is covered by our industry-leading [security and privacy policies](https://humansignal.com/security/).
 
-## Can I disable Ask AI?
+## How do I enable or disable AI features?
 
-Yes, contact us to disable this feature.
+You can enable AI features from the **Organization > Billing & Usage** page. Only users in the Owners role have access to view and modify this page. 
 
 ## HIPAA compliance
 

docs/source/guide/prompts_keys.md

@@ -18,6 +18,7 @@ There are two approaches to adding a model provider API key.
     * OpenAI
     * Vertex AI
     * Gemini
+    * Anthropic
 
 * In the second scenario, you add a separate API key per model. Examples include:
 
@@ -58,6 +59,14 @@ The JSON credentials are required. You can also optionally provide the project I
 
 Once added, all supported models will appear in the base model drop-down when you [draft your prompt](prompts_draft).
 
+## Anthropic API key
+
+You can only have one Anthropic key per organization. This grants you access to set of whitelisted models. For a list of these models, see [Supported base models](prompts_overview#Supported-base-models). 
+
+For information on getting an Anthropic API key, see [Anthropic - Accessing the API](https://docs.anthropic.com/en/api/getting-started#accessing-the-api).
+
+Once added, all supported models will appear in the base model drop-down when you [draft your prompt](prompts_draft).
+
 ## Azure OpenAI key
 
 Each Azure OpenAI key is tied to a specific deployment, and each deployment comprises a single OpenAI model. So if you want to use multiple models through Azure, you will need to create a deployment for each model and then add each key to Label Studio. 

docs/source/guide/prompts_overview.md

@@ -48,9 +48,10 @@ With Prompts, you can:
 
 | Provider | Supported models |
 | --- | --- |
-| **OpenAI** | gpt-3.5-turbo-16k* <br>gpt-3.5-turbo* <br>gpt-4 <br>gpt-4-turbo <br>gpt-4o <br>gpt-4o-mini <br>o3-mini<br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data.  |
+| **OpenAI** | gpt-3.5-turbo-16k* <br>gpt-3.5-turbo* <br>gpt-4 <br>gpt-4-turbo <br>gpt-4o <br>gpt-4o-mini <br>o3-mini <br>o1<br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data.  |
 | **Gemini** | gemini-2.0-flash-exp <br>gemini-1.5-flash <br>gemini-1.5-flash-8b <br>gemini-1.5-pro  |
 | **Vertex AI** | gemini-2.0-flash-exp <br>gemini-1.5-flash <br>gemini-1.5-pro   |
+| **Anthropic** | claude-3-5-haiku <br>claude-3-5-sonnet    |
 | **Azure OpenAI** | [Azure OpenAI chat-based models](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) <br><br>**Note:** We recommend against using GPT 3.5 models, as these can sometimes be prone to rate limit errors and are not compatible with Image data.  |
 | **Custom** | [Custom LLM](prompts_create#Add-OpenAI-Azure-OpenAI-or-a-custom-model) |