Merge branch 'main' into ilongin/11161-clickhouse-nullable

Author: ilongin

.github/workflows/tests.yml

@@ -106,7 +106,7 @@ jobs:
         shell: bash
 
       - name: Run E2E tests
-        run: nox -s tests-${{ matrix.pyv }} -- -m "e2e" $DISABLE_REMOTES_ARG
+        run: nox -s tests-${{ matrix.pyv }} -- -m "e2e" --cov-append $DISABLE_REMOTES_ARG
         shell: bash
 
       - name: Upload coverage report

docs/overrides/main.html

@@ -8,6 +8,16 @@
 <script type="text/javascript">
   !function () { var e, t, n; e = "14ffd92a6cbf5f2", t = function () { Reo.init({ clientID: "14ffd92a6cbf5f2" }) }, (n = document.createElement("script")).src = "https://static.reo.dev/" + e + "/reo.js", n.async = !0, n.onload = t, document.head.appendChild(n) }();
 </script>
+<script>
+  function initApollo() {
+    var n = Math.random().toString(36).substring(7), o = document.createElement("script");
+    o.src = "https://assets.apollo.io/micro/website-tracker/tracker.iife.js?nocache=" + n, o.async = !0, o.defer = !0,
+      o.onload = function () { window.trackingFunctions.onLoad({ appId: "66315101e9aa7501c79140d9" }) },
+      document.head.appendChild(o)
+  };
+  initApollo();
+</script>
+
 
 
 {% endblock %}

examples/llm_and_nlp/unstructured-embeddings-gen.py

@@ -106,11 +106,7 @@ examples = [
   "datachain[tests]",
   "defusedxml",
   "accelerate",
-  "unstructured_ingest[embed-huggingface]",
-  "unstructured[pdf]<0.16.12",
-  "pdfplumber==0.11.5",
   "huggingface_hub[hf_transfer]",
-  "onnx==1.16.1",
   "ultralytics==8.3.64",
   "open_clip_torch"
 ]

examples/llm_and_nlp/unstructured-summary-map.py

@@ -3,7 +3,6 @@
     QUERY_SCRIPT_CANCELED_EXIT_CODE,
     QUERY_SCRIPT_INVALID_LAST_STATEMENT_EXIT_CODE,
     Catalog,
-    parse_edatachain_file,
 )
 from .loader import get_catalog
 
@@ -13,5 +12,4 @@
     "QUERY_SCRIPT_INVALID_LAST_STATEMENT_EXIT_CODE",
     "Catalog",
     "get_catalog",
-    "parse_edatachain_file",
 ]