Merge branch 'main' into feature/web_scraping_connector_task

Author: Geoff-Robin

.env.template

@@ -16,7 +16,7 @@
 STRUCTURED_OUTPUT_FRAMEWORK="instructor"
 
 LLM_API_KEY="your_api_key"
-LLM_MODEL="openai/gpt-4o-mini"
+LLM_MODEL="openai/gpt-5-mini"
 LLM_PROVIDER="openai"
 LLM_ENDPOINT=""
 LLM_API_VERSION=""
@@ -30,10 +30,13 @@ EMBEDDING_DIMENSIONS=3072
 EMBEDDING_MAX_TOKENS=8191
 # If embedding key is not provided same key set for LLM_API_KEY will be used
 #EMBEDDING_API_KEY="your_api_key"
+# Note: OpenAI support up to 2048 elements and Gemini supports a maximum of 100 elements in an embedding batch,
+#       Cognee sets the optimal batch size for OpenAI and Gemini, but a custom size can be defined if necessary for other models
+#EMBEDDING_BATCH_SIZE=2048
 
 # If using BAML structured output these env variables will be used
 BAML_LLM_PROVIDER=openai
-BAML_LLM_MODEL="gpt-4o-mini"
+BAML_LLM_MODEL="gpt-5-mini"
 BAML_LLM_ENDPOINT=""
 BAML_LLM_API_KEY="your_api_key"
 BAML_LLM_API_VERSION=""
@@ -52,18 +55,18 @@ BAML_LLM_API_VERSION=""
 ################################################################################
 # Configure storage backend (local filesystem or S3)
 # STORAGE_BACKEND="local"  # Default: uses local filesystem
-# 
+#
 # -- To switch to S3 storage, uncomment and fill these: ---------------------
 # STORAGE_BACKEND="s3"
 # STORAGE_BUCKET_NAME="your-bucket-name"
 # AWS_REGION="us-east-1"
 # AWS_ACCESS_KEY_ID="your-access-key"
 # AWS_SECRET_ACCESS_KEY="your-secret-key"
-# 
+#
 # -- S3 Root Directories (optional) -----------------------------------------
 # DATA_ROOT_DIRECTORY="s3://your-bucket/cognee/data"
 # SYSTEM_ROOT_DIRECTORY="s3://your-bucket/cognee/system"
-# 
+#
 # -- Cache Directory (auto-configured for S3) -------------------------------
 # When STORAGE_BACKEND=s3, cache automatically uses S3: s3://BUCKET/cognee/cache
 # To override the automatic S3 cache location, uncomment:
@@ -176,7 +179,14 @@ ENABLE_BACKEND_ACCESS_CONTROL=False
 
 # Cognee Cloud API settings for syncing data to/from cloud infrastructure
 COGNEE_CLOUD_API_URL="http://localhost:8001"
-COGNEE_CLOUD_AUTH_TOKEN="your-auth-token"
+COGNEE_CLOUD_AUTH_TOKEN="your-api-key"
+
+################################################################################
+# UI Settings
+################################################################################
+
+# URL where the frontend is served, defaults to http://localhost:3000
+UI_APP_URL=http://localhost:3000
 
 ################################################################################
 #  🛠️ DEV Settings
@@ -196,6 +206,16 @@ LITELLM_LOG="ERROR"
 # DEFAULT_USER_EMAIL=""
 # DEFAULT_USER_PASSWORD=""
 
+################################################################################
+#  📂 AWS Settings
+################################################################################
+
+#AWS_REGION=""
+#AWS_ENDPOINT_URL=""
+#AWS_ACCESS_KEY_ID=""
+#AWS_SECRET_ACCESS_KEY=""
+#AWS_SESSION_TOKEN=""
+
 ------------------------------- END OF POSSIBLE SETTINGS -------------------------------
 
 

.github/ISSUE_TEMPLATE/documentation.yml

@@ -71,3 +71,4 @@ body:
           required: true
         - label: I have specified the location of the documentation issue
           required: true
+

.github/actions/cognee_setup/action.yml

@@ -24,7 +24,7 @@ runs:
       uses: astral-sh/setup-uv@v4
       with:
         enable-cache: true
-    
+
     - name: Rebuild uv lockfile
       shell: bash
       run: |
@@ -41,4 +41,4 @@ runs:
             EXTRA_ARGS="$EXTRA_ARGS --extra $extra"
           done
         fi
-        uv sync --extra api --extra docs --extra evals --extra gemini --extra codegraph --extra ollama --extra dev --extra neo4j $EXTRA_ARGS
+        uv sync --extra api --extra docs --extra evals --extra codegraph --extra ollama --extra dev --extra neo4j $EXTRA_ARGS

.github/core-team.txt

@@ -0,0 +1,12 @@
+# Core team GitHub logins (one per line). Lines may begin with @; case-insensitive.
+borisarzentar
+daukadolt
+dexters1
+hajdul88
+hande-k
+lxobr
+pazone
+siillee
+vasilije1990
+
+

.github/workflows/basic_tests.yml

@@ -188,6 +188,7 @@ jobs:
         uses: ./.github/actions/cognee_setup
         with:
           python-version: ${{ inputs.python-version }}
+          extra-dependencies: "baml"
 
       - name: Run Simple Examples
         run: uv run python ./examples/python/simple_example.py

.github/workflows/e2e_tests.yml

@@ -166,9 +166,6 @@ jobs:
             python-version: '3.11.x'
             extra-dependencies: "aws"
 
-        - name: Dependencies already installed
-          run: echo "Dependencies already installed in setup"
-
         - name: Run S3 Bucket Test
           env:
             ENV: 'dev'

.github/workflows/examples_tests.yml

@@ -1,5 +1,8 @@
 name: Reusable Examples Tests
 
+permissions:
+  contents: read
+
 on:
   workflow_call:
 
@@ -131,3 +134,28 @@ jobs:
           EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
           EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
         run: uv run python ./examples/python/memify_coding_agent_example.py
+
+  test-permissions-example:
+    name: Run Permissions Example
+    runs-on: ubuntu-22.04
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+
+      - name: Cognee Setup
+        uses: ./.github/actions/cognee_setup
+        with:
+          python-version: '3.11.x'
+
+      - name: Run Memify Tests
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
+          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
+          EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
+          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
+          EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
+        run: uv run python ./examples/python/permissions_example.py

.github/workflows/label-core-team.yml

@@ -0,0 +1,76 @@
+name: Label PRs from core team
+
+on:
+  pull_request_target:
+    types: [opened, reopened, synchronize, ready_for_review, edited]
+
+permissions:
+  contents: read
+  issues: write
+
+jobs:
+  label-core-team:
+    if: ${{ !github.event.pull_request.draft }}
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out base repository
+        uses: actions/checkout@v4
+        with:
+          repository: ${{ github.repository }}
+          ref: ${{ github.event.pull_request.base.ref }}
+
+      - name: Determine if PR author is a core team member
+        id: check_core
+        shell: bash
+        run: |
+          AUTHOR="${{ github.event.pull_request.user.login }}"
+          LIST_FILE=".github/core-team.txt"
+
+          if [ ! -f "$LIST_FILE" ]; then
+            echo "core=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          # Normalize author to lowercase and strip leading '@'
+          AUTHOR_NORM="$(echo "$AUTHOR" | tr '[:upper:]' '[:lower:]' | sed 's/^@//')"
+
+          # Compare against normalized list values (ignore comments/blank lines)
+          if awk -v author="$AUTHOR_NORM" '
+            BEGIN { found=0 }
+            {
+              line=$0
+              sub(/^[ \t]+|[ \t]+$/, "", line)
+              if (line ~ /^#/ || line == "") next
+              sub(/^@/, "", line)
+              line=tolower(line)
+              if (line == author) { found=1; exit }
+            }
+            END { exit(found ? 0 : 1) }
+          ' "$LIST_FILE"; then
+            echo "core=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "core=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Add core-team label
+        if: steps.check_core.outputs.core == 'true'
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const label = 'core-team';
+            const { owner, repo } = context.repo;
+            const prNumber = context.payload.pull_request.number;
+            try {
+              await github.rest.issues.addLabels({
+                owner,
+                repo,
+                issue_number: prNumber,
+                labels: [label],
+              });
+              core.info(`Label '${label}' added to PR #${prNumber}`);
+            } catch (error) {
+              core.warning(`Failed to add label: ${error.message}`);
+            }
+
+

.github/workflows/test_different_operating_systems.yml

@@ -43,7 +43,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ubuntu-22.04, macos-13, macos-15, windows-latest]
+        os: [ubuntu-22.04, macos-15, windows-latest]
       fail-fast: false
     steps:
       - name: Check out
@@ -79,7 +79,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
+        os: [ ubuntu-22.04, macos-15, windows-latest ]
       fail-fast: false
     steps:
       - name: Check out
@@ -115,7 +115,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
+        os: [ ubuntu-22.04, macos-15, windows-latest ]
       fail-fast: false
     steps:
       - name: Check out
@@ -151,7 +151,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
+        os: [ ubuntu-22.04, macos-15, windows-latest ]
       fail-fast: false
     steps:
       - name: Check out
@@ -180,7 +180,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
+        os: [ ubuntu-22.04, macos-15, windows-latest ]
       fail-fast: false
     steps:
       - name: Check out
@@ -210,7 +210,7 @@ jobs:
     strategy:
       matrix:
         python-version: ${{ fromJSON(inputs.python-versions) }}
-        os: [ ubuntu-22.04, macos-13, macos-15, windows-latest ]
+        os: [ ubuntu-22.04, macos-15, windows-latest ]
       fail-fast: false
     steps:
       - name: Check out

.github/workflows/test_llms.yml

@@ -27,7 +27,7 @@ jobs:
         env:
           LLM_PROVIDER: "gemini"
           LLM_API_KEY: ${{ secrets.GEMINI_API_KEY }}
-          LLM_MODEL: "gemini/gemini-1.5-flash"
+          LLM_MODEL: "gemini/gemini-2.0-flash"
           EMBEDDING_PROVIDER: "gemini"
           EMBEDDING_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           EMBEDDING_MODEL: "gemini/text-embedding-004"
@@ -83,4 +83,4 @@ jobs:
           EMBEDDING_MODEL: "openai/text-embedding-3-large"
           EMBEDDING_DIMENSIONS: "3072"
           EMBEDDING_MAX_TOKENS: "8191"
-        run: uv run python ./examples/python/simple_example.py
+        run: uv run python ./examples/python/simple_example.py