docs: photo search example (#924)

Author: badmonster0

docs/docs/examples/examples/photo_search.md

@@ -10,34 +10,47 @@ sidebar_custom_props:
 tags: [vector-index, multi-modal]
 ---
 
-import { GitHubButton, YouTubeButton } from '../../../src/components/GitHubButton';
+import { GitHubButton, YouTubeButton, DocumentationButton } from '../../../src/components/GitHubButton';
 
 <GitHubButton url="https://github.com/cocoindex-io/cocoindex/tree/main/examples/face_recognition"/>
 
-
-## What We Will Achieve
+## Overview
+We’ll walk through a comprehensive example of building a scalable face recognition pipeline. We’ll 
 - Detect all faces in the image and extract their bounding boxes
 - Crop and encode each face image into a 128-dimensional face embedding
 - Store metadata and vectors in a structured index to support queries like: 
 “Find all similar faces to this one” or “Search images that include this person”
 
+With this, you can build your own photo search app with face detection and search.
 
-## Indexing Flow
+## Flow Overview
+![Flow Overview](/img/examples/photo_search/flow.png)
 
-1. We ingest a list of images.
-2. For each image, we:
+1. Ingest the images.
+2. For each image,
     - Extract faces from the image.
     - Compute embeddings for each face.
-3. We  export the following fields to a table in Postgres with PGVector:
+3. Export following fields to a table in Postgres with PGVector:
     - Filename, rect, embedding for each face.
 
+## Setup
+- [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
+
+- Install Qdrant
+    ```sh
+    docker run -d -p 6334:6334 -p 6333:6333 qdrant/qdrant
+    ```
+
+- Install dependencies:
+    ```sh
+    pip install -e .
+    ```
 
-## Image Ingestion
+## Add source
 
 We monitor an `images/` directory using the built-in `LocalFile` source. All newly added files are automatically processed and indexed.
+
 ```python
-python
-CopyEdit
 @cocoindex.flow_def(name="FaceRecognition")
 def face_recognition_flow(flow_builder, data_scope):
     data_scope["images"] = flow_builder.add_source(
@@ -56,7 +69,6 @@ or [Azure Blob store](https://cocoindex.io/docs/ops/sources#azureblob).
 
 We use the `face_recognition` library under the hood, powered by dlib’s CNN-based face detector. Since the model is slow on large images, we downscale wide images before detection.
 
-
 ```python
 @cocoindex.op.function(
     cache=True,
@@ -109,9 +121,9 @@ with data_scope["images"].row() as image:
 ```
 
 After this step, each image has a list of detected faces and bounding boxes.
-
 Each detected face is cropped from the original image and stored as a PNG.
 
+![Extracted Faces](/img/examples/photo_search/extraction.png)
 
 ## Compute Face Embeddings
 
@@ -154,7 +166,6 @@ face_embeddings.collect(
     rect=face["rect"],
     embedding=face["embedding"],
 )
-
 ```
 
 We export to a Qdrant collection:
@@ -171,12 +182,12 @@ face_embeddings.export(
 
 Now you can run cosine similarity queries over facial vectors.
 
-CocoIndex supports 1-line switch with other vector databases like [Postgres](https://cocoindex.io/docs/ops/targets#postgres).
+CocoIndex supports 1-line switch with other vector databases.
+<DocumentationButton url="https://cocoindex.io/docs/ops/targets#postgres" text="Postgres" />
 
 ## Query the Index
 
 You can now build facial search apps or dashboards. For example:
-
 - Given a new face embedding, find the most similar faces
 - Find all face images that appear in a set of photos
 - Cluster embeddings to group visually similar people
@@ -187,3 +198,13 @@ For querying embeddings, check out [Image Search project](https://cocoindex.io/b
 If you’d like to see a full example on the query path with image match, give it a shout at 
 [our group](https://discord.com/invite/zpA9S2DR7s).
 
+## CocoInsight
+CocoInsight is a tool to help you understand your data pipeline and data index. It can now visualize identified sections of an image based on the bounding boxes and makes it easier to understand and evaluate AI extractions - seamlessly attaching computed features in the context of unstructured visual data.
+
+You can walk through the project step by step in [CocoInsight](https://www.youtube.com/watch?v=MMrpUfUcZPk) to see exactly how each field is constructed and what happens behind the scenes.
+
+```sh
+cocoindex server -ci main.py
+```
+
+Follow the url `https://cocoindex.io/cocoinsight`.  It connects to your local CocoIndex server, with zero pipeline data retention.