feast-dev · franciscojavierarceo · Jun 2, 2025 · Jun 2, 2025 · Jun 2, 2025 · franciscojavierarceo
@@ -65,99 +65,6 @@ Feast supports transformations that can be used to:
 * Normalize and preprocess features before serving to LLMs
 * Apply custom transformations to adapt features for specific LLM requirements
 
-## Getting Started with Feast for GenAI
-
-### Installation
-
-To use Feast with vector database support, install with the appropriate extras:
-
-```bash
-# For Milvus support
-pip install feast[milvus,nlp]
-
-# For Elasticsearch support
-pip install feast[elasticsearch]
-
-# For Qdrant support
-pip install feast[qdrant]
-
-# For SQLite support (Python 3.10 only)
-pip install feast[sqlite_vec]
-```
-
-### Configuration
-
-Configure your feature store to use a vector database as the online store:
-
-```yaml
-project: genai-project
-provider: local
-registry: data/registry.db
-online_store:
-  type: milvus
-  path: data/online_store.db
-  vector_enabled: true
-  embedding_dim: 384  # Adjust based on your embedding model
-  index_type: "IVF_FLAT"
-
-offline_store:
-  type: file
-entity_key_serialization_version: 3
-```
-
-### Defining Vector Features
-
-Create feature views with vector index support:
-
-```python
-from feast import FeatureView, Field, Entity
-from feast.types import Array, Float32, String
-
-document = Entity(
-    name="document_id",
-    description="Document identifier",
-    join_keys=["document_id"],
-)
-
-document_embeddings = FeatureView(
-    name="document_embeddings",
-    entities=[document],
-    schema=[
-        Field(
-            name="vector",
-            dtype=Array(Float32),
-            vector_index=True,  # Enable vector search
-            vector_search_metric="COSINE",  # Similarity metric
-        ),
-        Field(name="document_id", dtype=String),
-        Field(name="content", dtype=String),
-    ],
-    source=document_source,
-    ttl=timedelta(days=30),
-)
-```
-
-### Retrieving Similar Documents
-
-Use the `retrieve_online_documents_v2` method to find similar documents:
-
-```python
-# Generate query embedding
-query = "How does Feast support vector databases?"
-query_embedding = embed_text(query)  # Your embedding function
-
-# Retrieve similar documents
-context_data = store.retrieve_online_documents_v2(
-    features=[
-        "document_embeddings:vector",
-        "document_embeddings:document_id",
-        "document_embeddings:content",
-    ],
-    query=query_embedding,
-    top_k=3,
-    distance_metric='COSINE',
-).to_df()
-```
 ## Use Cases
 
 ### Document Question-Answering

@@ -105,6 +105,11 @@ class ReadDocumentRequest(BaseModel):
     file_path: str
 
 
+class SaveDocumentRequest(BaseModel):
+    file_path: str
+    data: dict
+
+
 def _get_features(request: GetOnlineFeaturesRequest, store: "feast.FeatureStore"):
     if request.feature_service:
         feature_service = store.get_feature_service(
@@ -375,6 +380,27 @@ async def read_document_endpoint(request: ReadDocumentRequest):
         except Exception as e:
             return {"error": str(e)}
 
+    @app.post("/save-document")
+    async def save_document_endpoint(request: SaveDocumentRequest):
+        try:
+            import json
+            import os
+            from pathlib import Path
+
+            file_path = Path(request.file_path).resolve()
+            if not str(file_path).startswith(os.getcwd()):
+                return {"error": "Invalid file path"}
+
+            base_name = file_path.stem
+            labels_file = file_path.parent / f"{base_name}-labels.json"
+
+            with open(labels_file, "w", encoding="utf-8") as file:
+                json.dump(request.data, file, indent=2, ensure_ascii=False)
+
+            return {"success": True, "saved_to": str(labels_file)}
+        except Exception as e:
+            return {"error": str(e)}
+
     @app.get("/chat")
     async def chat_ui():
         # Serve the chat UI

@@ -1495,6 +1495,7 @@ async def push_async(
         df: pd.DataFrame,
         allow_registry_cache: bool = True,
         to: PushMode = PushMode.ONLINE,
+        **kwargs,
     ):
         fvs = self._fvs_for_push_source_or_raise(push_source_name, allow_registry_cache)
 

@@ -7,10 +7,16 @@
 from fastapi import FastAPI, Response
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
+from pydantic import BaseModel
 
 import feast
 
 
+class SaveDocumentRequest(BaseModel):
+    file_path: str
+    data: dict
+
+
 def get_app(
     store: "feast.FeatureStore",
     project_id: str,
@@ -76,6 +82,26 @@ def read_registry():
             media_type="application/octet-stream",
         )
 
+    @app.post("/save-document")
+    async def save_document_endpoint(request: SaveDocumentRequest):
+        try:
+            import os
+            from pathlib import Path
+
+            file_path = Path(request.file_path).resolve()
+            if not str(file_path).startswith(os.getcwd()):
+                return {"error": "Invalid file path"}
+
+            base_name = file_path.stem
+            labels_file = file_path.parent / f"{base_name}-labels.json"
+
+            with open(labels_file, "w", encoding="utf-8") as file:
+                json.dump(request.data, file, indent=2, ensure_ascii=False)
+
+            return {"success": True, "saved_to": str(labels_file)}
+        except Exception as e:
+            return {"error": str(e)}
+
     # For all other paths (such as paths that would otherwise be handled by react router), pass to React
     @app.api_route("/p/{path_name:path}", methods=["GET"])
     def catch_all():

@@ -147,7 +147,7 @@ const FeastUISansProvidersInner = ({
                       element={<DatasetInstance />}
                     />
                     <Route
-                      path="document-labeling/"
+                      path="data-labeling/"
                       element={<DocumentLabelingPage />}
                     />
                     <Route path="permissions/" element={<PermissionsIndex />} />

@@ -136,18 +136,18 @@ interface DatasetCustomTabRegistrationInterface
   }: DatasetCustomTabProps) => JSX.Element;
 }
 
-// Type for Document Labeling Custom Tabs
-interface DocumentLabelingCustomTabProps {
+// Type for Data Labeling Custom Tabs
+interface DataLabelingCustomTabProps {
   id: string | undefined;
   feastObjectQuery: RegularFeatureViewQueryReturnType;
 }
-interface DocumentLabelingCustomTabRegistrationInterface
+interface DataLabelingCustomTabRegistrationInterface
   extends CustomTabRegistrationInterface {
   Component: ({
     id,
     feastObjectQuery,
     ...args
-  }: DocumentLabelingCustomTabProps) => JSX.Element;
+  }: DataLabelingCustomTabProps) => JSX.Element;
 }
 
 export type {
@@ -171,6 +171,6 @@ export type {
   FeatureCustomTabProps,
   DatasetCustomTabRegistrationInterface,
   DatasetCustomTabProps,
-  DocumentLabelingCustomTabRegistrationInterface,
-  DocumentLabelingCustomTabProps,
+  DataLabelingCustomTabRegistrationInterface,
+  DataLabelingCustomTabProps,
 };
@@ -132,13 +132,13 @@ const SideNav = () => {
           isSelected: useMatchSubpath(`${baseUrl}/data-set`),
         },
         {
-          name: "Document Labeling",
-          id: htmlIdGenerator("documentLabeling")(),
-          icon: <EuiIcon type="documentEdit" />,
+          name: "Data Labeling",
+          id: htmlIdGenerator("dataLabeling")(),
+          icon: <EuiIcon type="documentEdit" color="#006BB4" />,
           renderItem: (props) => (
-            <Link {...props} to={`${baseUrl}/document-labeling`} />
+            <Link {...props} to={`${baseUrl}/data-labeling`} />
           ),
-          isSelected: useMatchSubpath(`${baseUrl}/document-labeling`),
+          isSelected: useMatchSubpath(`${baseUrl}/data-labeling`),
         },
         {
           name: "Permissions",