Merge branch 'semantic-search-article---new' of https://github.com/su…

…perlinked/VectorHub into semantic-search-article---new

.github/workflows/data-fetch-push.yml

@@ -11,7 +11,7 @@ jobs:
 
     strategy:
       matrix:
-        python-version: [3.8]
+        python-version: [3.10.13]
 
     steps:
     - name: Checkout repository
@@ -22,9 +22,10 @@ jobs:
 
     - name: Add dependencies
       run: |
-        python -m pip install requests
-        python -m pip install tqdm
-        python -m pip install pypistats
+        python -m pip install --upgrade pip
+        pip install requests
+        pip install tqdm
+        pip install pypistats
 
     - name: Set pepy.tech API key
       run: |

.github/workflows/schema-authorize.yml

@@ -0,0 +1,76 @@
+name: Check Authorization for schema changes
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - 'docs/tools/vdb_table/**'
+
+jobs:
+  verify:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2
+
+      - name: Check if vendor.schema.json has changed
+        id: check_file_change
+        run: |
+          # Path of the specific file to check
+          file_path="docs/tools/vdb_table/vendor.schema.json"
+          
+          # Check if the file has changed
+          if git diff --name-only HEAD~1 | grep -q "$file_path"; then
+            echo "File $file_path has changed."
+            echo "file_changed=true" >> $GITHUB_ENV
+          else
+            echo "File $file_path has not changed."
+            echo "file_changed=false" >> $GITHUB_ENV
+          fi
+
+      - name: Get Commit Author
+        id: get_author
+        if: env.file_changed == 'true'
+        run: |
+          echo "commit_author=${{ github.actor }}" >> $GITHUB_ENV
+          echo "Commit author's username: ${{ github.actor }}"
+      
+      - name: Get GitHub Team Members
+        id: get_team_members
+        if: env.file_changed == 'true'
+        run: |
+          curl --fail -H "Authorization: token ${{ env.TOKEN }}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            https://api.github.com/orgs/superlinked/teams/vdb-table-maintainers/members \
+            > team.json
+        env:
+          TOKEN: ${{ secrets.VDB_CONTRIBUTION_CHECK_TOKEN }}
+
+      - name: Check if Commit Author is a Team Member
+        id: check_author
+        if: env.file_changed == 'true'
+        run: |
+          commit_author="${{ env.commit_author }}"
+          if jq -e ".[] | select(.login == \"$commit_author\")" team.json > /dev/null; then
+            echo "Authorized change."
+            echo "authorized=true" >> $GITHUB_ENV
+          else
+            echo "Unauthorized change detected!"
+            echo "authorized=false" >> $GITHUB_ENV
+          fi
+
+      - name: Send failure result to PR
+        uses: actions/github-script@v6
+        if: env.authorized == 'false'
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: "This PR contains schema changes. Please note that schema changes affect all vendors simultaneously.\n@${{env.commit_author}} Could you create a separate issue to discuss the necessity for this schema change with @superlinked/vdb-table-maintainers ? This will help ensure proper review and coordination."
+            })

docs/tools/vdb_table/data/activeloop.json

@@ -157,7 +157,7 @@
     "comment": ""
   },
   "github_stars": {
-    "value": 8056,
+    "value": 8117,
     "source_url": "https://github.com/activeloopai/deeplake",
     "comment": "",
     "value_90_days": 0
@@ -169,10 +169,10 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 895132,
+    "value": 964748,
     "source_url": "https://pypi.org/project/deeplake/",
     "comment": "",
-    "value_90_days": 189366
+    "value_90_days": 160684
   },
   "npm_downloads": {
     "value": 0,

docs/tools/vdb_table/data/aerospike.json

@@ -178,10 +178,10 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 1034,
+    "value": 1872,
     "source_url": "https://pypi.org/project/aerospike-vector/",
     "comment": "",
-    "value_90_days": 428
+    "value_90_days": 1053
   },
   "npm_downloads": {
     "value": 0,

docs/tools/vdb_table/data/anariai.json

@@ -174,10 +174,10 @@
     "value_90_days": 0
   },
   "npm_downloads": {
-    "value": 4781,
+    "value": 5132,
     "source_url": "https://www.npmjs.com/package/epsillajs",
     "comment": "",
-    "value_90_days": 564
+    "value_90_days": 628
   },
   "crates_io_downloads": {
     "value": 0,

docs/tools/vdb_table/data/apachecassandra.json

@@ -157,33 +157,33 @@
     "comment": "via Lucene"
   },
   "github_stars": {
-    "value": 8718,
+    "value": 8804,
     "source_url": "https://github.com/apache/cassandra",
     "comment": "",
     "value_90_days": 0
   },
   "docker_pulls": {
-    "value": 215353353,
+    "value": 216244777,
     "source_url": "https://hub.docker.com/_/cassandra",
     "comment": "",
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 82236806,
+    "value": 86110753,
     "source_url": "https://pypi.org/project/cassandra-driver/",
     "comment": "",
-    "value_90_days": 8344646
+    "value_90_days": 9251369
   },
   "npm_downloads": {
-    "value": 4563765,
+    "value": 4616203,
     "source_url": "https://www.npmjs.com/package/cassandra-driver",
     "comment": "",
-    "value_90_days": 893050
+    "value_90_days": 859771
   },
   "crates_io_downloads": {
-    "value": 87444,
+    "value": 89981,
     "source_url": "https://crates.io/crates/cassandra",
     "comment": "",
-    "value_90_days": 997
+    "value_90_days": 944
   }
 }

docs/tools/vdb_table/data/apachesolr.json

@@ -157,33 +157,33 @@
     "comment": "via Lucene"
   },
   "github_stars": {
-    "value": 1161,
+    "value": 1207,
     "source_url": "https://github.com/apache/solr",
     "comment": "",
     "value_90_days": 0
   },
   "docker_pulls": {
-    "value": 343638008,
+    "value": 344130245,
     "source_url": "https://hub.docker.com/_/solr",
     "comment": "",
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 11715086,
+    "value": 12071484,
     "source_url": "https://pypi.org/project/pysolr/",
     "comment": "",
-    "value_90_days": 911770
+    "value_90_days": 905911
   },
   "npm_downloads": {
-    "value": 613841,
+    "value": 593353,
     "source_url": "https://www.npmjs.com/package/solr-client",
     "comment": "",
-    "value_90_days": 104883
+    "value_90_days": 107721
   },
   "crates_io_downloads": {
-    "value": 1417,
+    "value": 1530,
     "source_url": "https://crates.io/crates/solr",
     "comment": "",
-    "value_90_days": 161
+    "value_90_days": 213
   }
 }

docs/tools/vdb_table/data/aperturedb.json

@@ -168,16 +168,16 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 147396,
+    "value": 179145,
     "source_url": "https://pypi.org/project/aperturedb/",
     "comment": "",
-    "value_90_days": 15938
+    "value_90_days": 38906
   },
   "npm_downloads": {
-    "value": 19299,
+    "value": 18333,
     "source_url": "https://www.npmjs.com/package/aperture",
     "comment": "",
-    "value_90_days": 1779
+    "value_90_days": 1614
   },
   "crates_io_downloads": {
     "value": 0,

docs/tools/vdb_table/data/azureai.json

@@ -179,16 +179,16 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 29413547,
+    "value": 32490575,
     "source_url": "https://pypi.org/project/azure-ai-ml/",
     "comment": "",
-    "value_90_days": 9637051
+    "value_90_days": 8722904
   },
   "npm_downloads": {
-    "value": 6097460,
+    "value": 7087026,
     "source_url": "https://www.npmjs.com/package/@azure/openai",
     "comment": "",
-    "value_90_days": 2040803
+    "value_90_days": 2315453
   },
   "crates_io_downloads": {
     "value": 0,

docs/tools/vdb_table/data/chroma.json

@@ -157,7 +157,7 @@
     "comment": ""
   },
   "github_stars": {
-    "value": 14644,
+    "value": 15097,
     "source_url": "https://github.com/chroma-core/chroma",
     "comment": "",
     "value_90_days": 0
@@ -169,21 +169,21 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 18011687,
+    "value": 20502882,
     "source_url": "https://pypi.org/project/chromadb/",
     "comment": "",
-    "value_90_days": 5039678
+    "value_90_days": 5610849
   },
   "npm_downloads": {
-    "value": 1645854,
+    "value": 1837352,
     "source_url": "https://www.npmjs.com/package/chromadb",
     "comment": "",
-    "value_90_days": 457417
+    "value_90_days": 501691
   },
   "crates_io_downloads": {
-    "value": 12346,
+    "value": 15009,
     "source_url": "https://crates.io/crates/chromadb",
     "comment": "",
-    "value_90_days": 1305
+    "value_90_days": 1569
   }
 }

docs/tools/vdb_table/data/clickhouse.json

@@ -156,7 +156,7 @@
     "comment": "HNSW via USearch"
   },
   "github_stars": {
-    "value": 36818,
+    "value": 37360,
     "source_url": "https://github.com/ClickHouse/ClickHouse",
     "comment": "",
     "value_90_days": 0
@@ -168,21 +168,21 @@
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 199826,
+    "value": 202650,
     "source_url": "https://pypi.org/project/clickhouse/",
     "comment": "",
-    "value_90_days": 8934
+    "value_90_days": 7863
   },
   "npm_downloads": {
-    "value": 9471991,
+    "value": 12045811,
     "source_url": "https://www.npmjs.com/package/@clickhouse/client",
     "comment": "",
-    "value_90_days": 4058895
+    "value_90_days": 5238702
   },
   "crates_io_downloads": {
-    "value": 420935,
+    "value": 467732,
     "source_url": "https://crates.io/crates/clickhouse",
     "comment": "",
-    "value_90_days": 89318
+    "value_90_days": 44889
   }
 }

docs/tools/vdb_table/data/couchbase.json

@@ -135,33 +135,33 @@
     "comment": "Automatic algorithm selection between: IdMap2,Flat, IVF,Flat, IVF,SQ8"
   },
   "github_stars": {
-    "value": 1620,
+    "value": 1625,
     "source_url": "https://github.com/couchbase/couchbase-lite-ios",
     "comment": "",
     "value_90_days": 0
   },
   "docker_pulls": {
-    "value": 87084773,
+    "value": 87163266,
     "source_url": "https://hub.docker.com/_/couchbase",
     "comment": "50M+",
     "value_90_days": 0
   },
   "pypi_downloads": {
-    "value": 13244513,
+    "value": 13698847,
     "source_url": "https://pypi.org/project/couchbase/",
     "comment": "",
-    "value_90_days": 1255480
+    "value_90_days": 1064839
   },
   "npm_downloads": {
-    "value": 1122527,
+    "value": 1138528,
     "source_url": "https://www.npmjs.com/package/couchbase",
     "comment": "",
-    "value_90_days": 202251
+    "value_90_days": 208934
   },
   "crates_io_downloads": {
-    "value": 37475,
+    "value": 38326,
     "source_url": "https://crates.io/crates/couchbase",
     "comment": "",
-    "value_90_days": 883
+    "value_90_days": 1105
   }
 }