Merge branch 'main' into fix_drift_search_doc

.gitignore

@@ -50,3 +50,9 @@ site/
 docsite/
 .yarn/
 .pnp*
+
+# PyCharm
+.idea/
+
+# Jupyter notebook
+.ipynb_checkpoints/

.semversioner/0.4.1.json

@@ -0,0 +1,34 @@
+{
+  "changes": [
+    {
+      "description": "Add update cli entrypoint for incremental indexing",
+      "type": "patch"
+    },
+    {
+      "description": "Allow some cicd jobs to skip PRs dedicated to doc updates only.",
+      "type": "patch"
+    },
+    {
+      "description": "Fix a file paths issue in the viz guide.",
+      "type": "patch"
+    },
+    {
+      "description": "Fix optional covariates update in incremental indexing",
+      "type": "patch"
+    },
+    {
+      "description": "Raise error on empty deltas for inc indexing",
+      "type": "patch"
+    },
+    {
+      "description": "add visualization guide to doc site",
+      "type": "patch"
+    },
+    {
+      "description": "fix streaming output error",
+      "type": "patch"
+    }
+  ],
+  "created_at": "2024-11-08T23:13:05+00:00",
+  "version": "0.4.1"
+}

.semversioner/next-release/minor-20241113010525824646.json

@@ -0,0 +1,4 @@
+{
+  "type": "minor",
+  "description": "Data model changes."
+}

.semversioner/next-release/patch-20241031230557819462.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Cleanup of artifact outputs/schemas."
+}

.semversioner/next-release/patch-20241106004612053719.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Implement dynamic community selection to global search"
+}

.semversioner/next-release/patch-20241114012244853718.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Centralized prompts and export all for easier injection."
+}

.semversioner/next-release/patch-20241114182805008149.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Add Parquet as part of the default emitters when not pressent"
+}

CHANGELOG.md

@@ -1,13 +1,22 @@
 # Changelog
-
 Note: version releases in the 0.x.y range may introduce breaking changes.
 
+## 0.4.1
+
+- patch: Add update cli entrypoint for incremental indexing
+- patch: Allow some CI/CD jobs to skip PRs dedicated to doc updates only.
+- patch: Fix a file paths issue in the viz guide.
+- patch: Fix optional covariates update in incremental indexing
+- patch: Raise error on empty deltas for inc indexing
+- patch: add visualization guide to doc site
+- patch: fix streaming output error
+
 ## 0.4.0
 
 - minor: Add Incremental Indexing
 - minor: Added DRIFT graph reasoning query module
 - minor: embeddings moved to a different workflow
-- minor: Add DRIFT search cli and example notebook
+- patch: Add DRIFT search cli and example notebook
 - patch: Add config for incremental updates
 - patch: Add embeddings to subflow.
 - patch: Add naive community merge using time period

docs/config/env_vars.md

@@ -9,8 +9,8 @@ If the embedding target is `all`, and you want to only embed a subset of these f
 ### Embedded Fields
 
 - `text_unit.text`
-- `document.raw_content`
-- `entity.name`
+- `document.text`
+- `entity.title`
 - `entity.description`
 - `relationship.description`
 - `community.title`

docs/examples_notebooks/drift_search.ipynb

@@ -204,7 +204,7 @@
     "# load description embeddings to an in-memory lancedb vectorstore\n",
     "# to connect to a remote db, specify url and port values.\n",
     "description_embedding_store = LanceDBVectorStore(\n",
-    "    collection_name=\"entity_description_embeddings\",\n",
+    "    collection_name=\"default-entity-description\",\n",
     ")\n",
     "description_embedding_store.connect(db_uri=LANCEDB_URI)\n",
     "entity_description_embeddings = store_entity_semantic_embeddings(\n",