Dev minor (#1436)

* fix-actions (#1426) * up * modify * add to github path * Contextual Chunk Enrichment (#1433) * add semantic chunking * working * precommit * pre-commits * Entity Deduplication (#1431) * Modify graphrag prompt (#1421) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * up * add tests * Feature/include vectors option document chunks (#1419) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * add option to include vectors in document chunks * checkin * update vector --------- Co-authored-by: Nolan Tremelling <[email protected]> * Allow env var to set the default R2R deployment for the dashboard (#1417) * modify community_summary_prompt function and corresponding prompt * add tests * up * Feature/various documentation tweaks (#1422) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * add option to include vectors in document chunks * checkin * update vector * some various documentation tweaks * some various documentation tweaks --------- Co-authored-by: Nolan Tremelling <[email protected]> * Graphrag tests (#1418) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * up * add tests --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * Modify graphrag tests timeouts (#1416) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * modify timeouts --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * feat: Make prompt provider methods asynchronous (comments below) (#1415) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * feat: Make prompt provider methods asynchronous --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * up * up --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * Add routes, service level methods around conversations (#1420) * Add routes, service level methods around conversations * Slight refactor to match project conventions, add JS methods * Updated JS methods * JS docs * Add python * Update JS user tests * add deduplication pipe, workflow, api, sdk, cli * add summary workflow * bug fixes * pre-commit * working * search working * adding dedup test files * modify the update query * precommit * more testing --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * Refactor Python SDK for Intellisense, Thread Safety (#1430) * Refactor Python SDK * Fix CLI after SDK changes * Add convo to agent * Update conversation error handling, JS * Remove unused, bad import * Feature/cleanup refactor vector collection (#1432) * Feature/include vectors option document chunks (#1419) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * add option to include vectors in document chunks * checkin * update vector --------- Co-authored-by: Nolan Tremelling <[email protected]> * Allow env var to set the default R2R deployment for the dashboard (#1417) * Feature/various documentation tweaks (#1422) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * add option to include vectors in document chunks * checkin * update vector * some various documentation tweaks * some various documentation tweaks --------- Co-authored-by: Nolan Tremelling <[email protected]> * Graphrag tests (#1418) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * up * add tests --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * Modify graphrag tests timeouts (#1416) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * modify timeouts --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * feat: Make prompt provider methods asynchronous (comments below) (#1415) * Fix async JSON parsing (#1408) * Fix async JSON parsing * Remove score completion from js * clean up js * lockfile * Feature/build custom logger (#1409) * building a custom logger for r2r * fix log * maintain bkwd compat * Feature/add kg description prompt (#1411) * add kg desc prompt * add kg desc prompt * add kg desc prompt * fix prompt name * separate test run freq (#1412) * separate test run freq * task_id check fix * add ingestion docs * updatet * add * rm old prompts * rm old prompots * rm old prompts * rm old prompts * Prod fixes + enhancements (#1407) * change default settings back to fp32 * add logging and cache triples * up * up * pre-commit and cleanups * making community summary prompt async * up * up * revert prompt changes * up * up * modify default * bump test timeout due to stricter concurrency limits * bump sleep * rm ubuntu from windows/mac workflows * feat: Make prompt provider methods asynchronous --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> Co-authored-by: emrgnt-cmplxty <[email protected]> * bump pyproject version * first commit * towards slimmer vector implementation logic * up * iterate * up * checkin * up * work doc chunks * working vector search * working full text search * remove asyncpg * passing vector tests * up * merge * rm pytest * up * up * fix delete * up * up --------- Co-authored-by: Nolan Tremelling <[email protected]> Co-authored-by: Shreyas Pimpalgaonkar <[email protected]> * Add tests + Cleanup (#1437) * up * add tests * test rename to sdk * up * fix tests * typo * modify chunk enrichment prompt (#1438) * modify prompt * up * Fix type error on port argument of CLI (#1439) * finish (#1440) * finish * up * fix * fix * up * fix * final cleanups * fix naming convention * fix schema error * increase timeout * split graphrag actions * fix collection exists error * up (#1442) * Add error message (#1443) * up * sdk fix * locally testing build * up docs (#1445) * checkin work (#1444) * checkin work * finish index functionality extension * fix concurrency * add alembic (#1446) * Prompt Tuning (#1447) * Check in * Fix after merging dev-minor in * Ensure to not cause int overflow with hatchet (#1454) * Bump JS (#1456) * Ensure to not cause int overflow with hatchet * bump js * improve migration implementation (#1452) * improve migration implementation * refine migrations to include kg * add alembic cli * extend documentation * extend docs and all that * Revert change of default behaviour of entities endpoint, docs, tests (#1455) * change def behavior of entities + delete endpoint * pre-commit * add deduplication tests * Delete graph (#1450) * up docs * up * up * rename to raw_chunks * up * add tests * up * up * change default * change cli * separate out deduplication tests * change run type in the test * up * up * add test concurrency * up * rm concurrency groups * rm dedup tests * remove json * tests * up * fix lock * Update postgres.py * Feature/merge dev minor main (#1457) * add run without orchestration (#1448) * add run without orchestration * bump versions * bump versions * bump versions * fix * up * add end points * add run without orchestration (#1448) (#1458) * add run without orchestration * bump versions * bump versions * bump versions * fix * up * sync migration changes * Ensure that we await ingest files in ingest_files method (#1460) * Nolan/await update files (#1461) * Ensure that we await ingest files in ingest_files method * Await update files as well * Docs changes (#1462) * up * up * up * up * fix failed find and replace (#1463) * fix failed find and replace * fix * Fix JS Client for Ingest Chunks (#1464) * Ensure that we await ingest files in ingest_files method * Await update files as well * Fix js client --------- Co-authored-by: Shreyas Pimpalgaonkar <[email protected]> Co-authored-by: Nolan Tremelling <[email protected]>
SciPhi-AI · Oct 23, 2024 · bc53dc9 · bc53dc9
1 parent eec527b
commit bc53dc9
Show file tree

Hide file tree

Showing 172 changed files with 10,788 additions and 4,650 deletions.
diff --git a/.github/actions/run-cli-graphrag-deduplication-tests/action.yml b/.github/actions/run-cli-graphrag-deduplication-tests/action.yml
@@ -0,0 +1,39 @@
+name: 'Run CLI Graphrag Tests'
+description: 'Runs CLI graphrag tests for R2R'
+runs:
+  using: "composite"
+  steps:
+    - name: Ingest sample file (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_ingest_sample_file_2_cli
+
+    - name: Create the graph (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_create_graph_sample_file_cli
+
+    - name: Deduplicate entities (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_deduplicate_entities_sample_file_cli
+
+    - name: Enrich the graph (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_enrich_graph_sample_file_cli
+
+    - name: Search over the graph (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_search_sample_file_cli
+
+    - name: Delete the graph (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_delete_graph_sample_file_cli
+
+    - name: Delete the graph with cascading (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_delete_graph_with_cascading_sample_file_cli
diff --git a/.github/actions/run-cli-graphrag-tests/action.yml b/.github/actions/run-cli-graphrag-tests/action.yml
@@ -3,22 +3,32 @@ description: 'Runs CLI graphrag tests for R2R'
 runs:
   using: "composite"
   steps:
-    - name: Ingest sample file (SDK)
+    - name: Ingest sample file (CLI)
       working-directory: ./py
       shell: bash
       run: poetry run python tests/integration/runner_cli.py test_ingest_sample_file_2_cli
 
-    - name: Create the graph (SDK)
+    - name: Create the graph (CLI)
       working-directory: ./py
       shell: bash
       run: poetry run python tests/integration/runner_cli.py test_kg_create_graph_sample_file_cli
 
-    - name: Enrich the graph (SDK)
+    - name: Enrich the graph (CLI)
       working-directory: ./py
       shell: bash
       run: poetry run python tests/integration/runner_cli.py test_kg_enrich_graph_sample_file_cli
 
-    - name: Search over the graph (SDK)
+    - name: Search over the graph (CLI)
       working-directory: ./py
       shell: bash
       run: poetry run python tests/integration/runner_cli.py test_kg_search_sample_file_cli
+
+    - name: Delete the graph (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_delete_graph_sample_file_cli
+
+    - name: Delete the graph with cascading (CLI)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_cli.py test_kg_delete_graph_with_cascading_sample_file_cli
diff --git a/.github/actions/run-sdk-graphrag-deduplication-tests/action.yml b/.github/actions/run-sdk-graphrag-deduplication-tests/action.yml
@@ -0,0 +1,39 @@
+name: 'Run SDK Graphrag Tests'
+description: 'Runs SDK graphrag tests for R2R'
+runs:
+  using: "composite"
+  steps:
+    - name: Ingest sample file (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_ingest_sample_file_2_sdk
+
+    - name: Create the graph (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_create_graph_sample_file_sdk
+
+    - name: Deduplicate entities (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_deduplicate_entities_sample_file_sdk
+
+    - name: Enrich the graph (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_enrich_graph_sample_file_sdk
+
+    - name: Search over the graph (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_search_sample_file_sdk
+
+    - name: Delete the graph (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_delete_graph_sample_file_sdk
+
+    - name: Delete the graph with cascading (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_delete_graph_with_cascading_sample_file_sdk
diff --git a/.github/actions/run-sdk-graphrag-tests/action.yml b/.github/actions/run-sdk-graphrag-tests/action.yml
@@ -22,3 +22,13 @@ runs:
       working-directory: ./py
       shell: bash
       run: poetry run python tests/integration/runner_sdk.py test_kg_search_sample_file_sdk
+
+    - name: Delete the graph (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_delete_graph_sample_file_sdk
+
+    - name: Delete the graph with cascading (SDK)
+      working-directory: ./py
+      shell: bash
+      run: poetry run python tests/integration/runner_sdk.py test_kg_delete_graph_with_cascading_sample_file_sdk
diff --git a/.github/actions/setup-postgres-ext/action.yml b/.github/actions/setup-postgres-ext/action.yml
@@ -32,39 +32,60 @@ runs:
 
     - name: Setup PostgreSQL on Windows
       if: inputs.os == 'windows-latest'
-      shell: pwsh
+      shell: cmd
       run: |
-        choco install postgresql15 --params '/Password:postgres' --force
 
-        $env:PATH += ";C:\Program Files\PostgreSQL\15\bin"
-        $env:PGPASSWORD = 'postgres'
+        echo Starting PostgreSQL setup and pgvector installation...
+
+        echo Installing PostgreSQL...
+        choco install postgresql15 --params "/Password:postgres" --force
+
+        echo Updating PATH and setting PGPASSWORD...
+        set PATH=%PATH%;C:\Program Files\PostgreSQL\15\bin
+        set PGPASSWORD=postgres
+        echo PATH updated and PGPASSWORD set.
+
+        echo Altering PostgreSQL user password...
         psql -U postgres -c "ALTER USER postgres PASSWORD 'postgres';"
+        echo PostgreSQL user password altered.
 
-        # Install Visual Studio Build Tools
+        echo Installing Visual Studio Build Tools...
         choco install visualstudio2022buildtools --package-parameters "--add Microsoft.VisualStudio.Workload.VCTools --includeRecommended --passive --norestart"
+        echo Visual Studio Build Tools installed.
 
-        # Set up environment for building pgvector
-        $vcvars64Path = "C:\Program Files\Microsoft Visual Studio\2022\BuildTools\VC\Auxiliary\Build\vcvars64.bat"
-        cmd.exe /c "call `"$vcvars64Path`" && set > %temp%\vcvars.txt"
-        Get-Content "$env:temp\vcvars.txt" | Foreach-Object {
-          if ($_ -match "^(.*?)=(.*)$") {
-            Set-Content "env:\$($matches[1])" $matches[2]
-          }
-        }
-
-        # Clone and build pgvector
-        $env:PGROOT = "C:\Program Files\PostgreSQL\15"
-        Set-Location -Path $env:TEMP
+        echo Setting up Visual Studio environment...
+        call "C:\Program Files\Microsoft Visual Studio\2022\BuildTools\VC\Auxiliary\Build\vcvars64.bat"
+        echo Visual Studio environment set up.
+
+        echo Cloning and building pgvector...
+        set PGROOT=C:\Program Files\PostgreSQL\15
+        cd /d %TEMP%
         git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git
-        Set-Location -Path "$env:TEMP\pgvector"
+        cd pgvector
+        echo pgvector cloned.
+
+        echo Creating vector extension...
+        psql -U postgres -c "CREATE EXTENSION vector;"
+        echo Vector extension created.
+
+        echo Building pgvector...
         nmake /F Makefile.win
+        echo pgvector built.
+
+        echo Installing pgvector...
         nmake /F Makefile.win install
+        echo pgvector installed.
 
-        psql -U postgres -c "CREATE EXTENSION vector;"
+        echo Setting max_connections to 1024...
+        echo max_connections = 1024 >> "C:\Program Files\PostgreSQL\15\data\postgresql.conf"
+        echo max_connections set.
 
-        # Set max_connections to 1024
-        Add-Content -Path "C:\Program Files\PostgreSQL\15\data\postgresql.conf" -Value "max_connections = 1024"
-        Restart-Service postgresql-x64-15
+        echo Restarting PostgreSQL service...
+        net stop postgresql-x64-15
+        net start postgresql-x64-15
+        echo PostgreSQL service restarted.
+
+        echo Setup complete!
 
     - name: Setup PostgreSQL on macOS
       if: inputs.os == 'macos-latest'

diff --git a/.github/actions/setup-python-full/action.yml b/.github/actions/setup-python-full/action.yml
@@ -26,8 +26,9 @@ runs:
 
     - name: Install Poetry and dependencies on Windows
       if: inputs.os == 'windows-latest'
-      shell: pwsh
+      shell: cmd
       run: |
-        (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-        $env:PATH += ";$env:USERPROFILE\AppData\Roaming\Python\Scripts"
-        cd py; poetry install -E core -E ingestion-bundle
+        python -c "import urllib.request; print(urllib.request.urlopen('https://install.python-poetry.org').read().decode())" > install-poetry.py
+        python install-poetry.py
+        echo %USERPROFILE%\AppData\Roaming\Python\Scripts >> %GITHUB_PATH%
+        cd py && poetry install -E core -E ingestion-bundle
diff --git a/.github/actions/setup-python-light/action.yml b/.github/actions/setup-python-light/action.yml
@@ -24,5 +24,7 @@ runs:
       shell: pwsh
       run: |
         (Invoke-WebRequest -Uri https://install.python-poetry.org -UseBasicParsing).Content | python -
-        $env:PATH += ";$env:USERPROFILE\AppData\Roaming\Python\Scripts"
-        cd py; poetry install -E core -E ingestion-bundle
+        $env:PATH += ";$env:APPDATA\Python\Scripts"
+        poetry --version
+        cd py
+        poetry install -E core -E ingestion-bundle
diff --git a/.github/actions/start-r2r-full/action.yml b/.github/actions/start-r2r-full/action.yml
@@ -12,4 +12,4 @@ runs:
     shell: bash
     run: |
       cd py
-      poetry run r2r serve --docker --full --config-name=full
+      poetry run r2r serve --docker --full --config-name=full --build --image=r2r-local
diff --git a/.github/workflows/r2r-full-py-integration-tests-graphrag.yml b/.github/workflows/r2r-full-py-integration-tests-graphrag.yml
@@ -0,0 +1,56 @@
+name: R2R Full Python Integration Test (ubuntu)
+
+on:
+  push:
+    branches:
+      - dev
+      - dev-minor
+  pull_request:
+    branches:
+      - dev
+      - dev-minor
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+        test_category:
+          - cli-graphrag
+          - sdk-graphrag
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      TELEMETRY_ENABLED: 'false'
+      R2R_PROJECT_NAME: r2r_default
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python and install dependencies
+        uses: ./.github/actions/setup-python-full
+        with:
+          os: ${{ matrix.os }}
+
+      - name: Setup and start Docker
+        uses: ./.github/actions/setup-docker
+
+      - name: Login Docker
+        uses: ./.github/actions/login-docker
+        with:
+          docker_username: ${{ secrets.RAGTORICHES_DOCKER_UNAME }}
+          docker_password: ${{ secrets.RAGTORICHES_DOCKER_TOKEN }}
+
+      - name: Start R2R Full server
+        uses: ./.github/actions/start-r2r-full
+
+      - name: Run CLI GraphRAG Tests
+        if: matrix.test_category == 'cli-graphrag'
+        uses: ./.github/actions/run-cli-graphrag-tests
+
+      - name: Run SDK GraphRAG Tests
+        if: matrix.test_category == 'sdk-graphrag'
+        uses: ./.github/actions/run-sdk-graphrag-tests
diff --git a/.github/workflows/r2r-full-py-integration-tests-mac-and-windows.yml b/.github/workflows/r2r-full-py-integration-tests-mac-and-windows.yml
@@ -79,4 +79,4 @@ jobs:
 
       - name: Run SDK GraphRAG Tests
         if: matrix.test_category == 'sdk-graphrag'
-        uses: ./.github/actions/run-cli-graphrag-tests
+        uses: ./.github/actions/run-sdk-graphrag-tests
diff --git a/.github/workflows/r2r-full-py-integration-tests.yml b/.github/workflows/r2r-full-py-integration-tests.yml
@@ -21,12 +21,10 @@ jobs:
         test_category:
           - cli-ingestion
           - cli-retrieval
-          - cli-graphrag
           - sdk-ingestion
           - sdk-retrieval
           - sdk-auth
           - sdk-collections
-          - sdk-graphrag
     env:
       OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
       TELEMETRY_ENABLED: 'false'
@@ -61,10 +59,6 @@ jobs:
         if: matrix.test_category == 'cli-retrieval'
         uses: ./.github/actions/run-cli-retrieval-tests
 
-      - name: Run CLI GraphRAG Tests
-        if: matrix.test_category == 'cli-graphrag'
-        uses: ./.github/actions/run-cli-graphrag-tests
-
       - name: Run SDK Ingestion Tests
         if: matrix.test_category == 'sdk-ingestion'
         uses: ./.github/actions/run-sdk-ingestion-tests
@@ -80,7 +74,3 @@ jobs:
       - name: Run SDK Collections Tests
         if: matrix.test_category == 'sdk-collections'
         uses: ./.github/actions/run-sdk-collections-tests
-
-      - name: Run SDK GraphRAG Tests
-        if: matrix.test_category == 'sdk-graphrag'
-        uses: ./.github/actions/run-cli-graphrag-tests
diff --git a/.github/workflows/r2r-light-py-integration-tests-graphrag.yml b/.github/workflows/r2r-light-py-integration-tests-graphrag.yml
@@ -0,0 +1,59 @@
+# yaml-language-server: $schema=https://json.schemastore.org/github-workflow.json
+
+name: R2R Light Python Integration Test (ubuntu)
+
+on:
+  push:
+    branches:
+      - dev
+      - dev-minor
+  pull_request:
+    branches:
+      - dev
+      - dev-minor
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+        test_category:
+          - cli-graphrag
+          - sdk-graphrag
+    env:
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      TELEMETRY_ENABLED: 'false'
+      R2R_POSTGRES_HOST: localhost
+      R2R_POSTGRES_DBNAME: postgres
+      R2R_POSTGRES_PORT: '5432'
+      R2R_POSTGRES_PASSWORD: postgres
+      R2R_POSTGRES_USER: postgres
+      R2R_PROJECT_NAME: r2r_default
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python and install dependencies
+        uses: ./.github/actions/setup-python-light
+        with:
+          os: ${{ matrix.os }}
+
+      - name: Setup and start PostgreSQL
+        uses: ./.github/actions/setup-postgres-ext
+        with:
+          os: ${{ matrix.os }}
+
+      - name: Start R2R Light server
+        uses: ./.github/actions/start-r2r-light
+
+      - name: Run CLI GraphRAG Tests
+        if: matrix.test_category == 'cli-graphrag'
+        uses: ./.github/actions/run-cli-graphrag-tests
+
+      - name: Run SDK GraphRAG Tests
+        if: matrix.test_category == 'sdk-graphrag'
+        uses: ./.github/actions/run-sdk-graphrag-tests