cocoindex 0.1.48__tar.gz → 0.1.50__tar.gz

{cocoindex-0.1.48 → cocoindex-0.1.50}/Cargo.lock

@@ -676,16 +676,43 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "edca88bc138befd0323b20752846e6587272d3b03b0343c8ea28a6f819e6e71f"
 dependencies = [
  "async-trait",
- "axum-core",
+ "axum-core 0.4.5",
  "bytes",
  "futures-util",
  "http 1.3.1",
  "http-body 1.0.1",
  "http-body-util",
+ "itoa",
+ "matchit 0.7.3",
+ "memchr",
+ "mime",
+ "percent-encoding",
+ "pin-project-lite",
+ "rustversion",
+ "serde",
+ "sync_wrapper",
+ "tower 0.5.2",
+ "tower-layer",
+ "tower-service",
+]
+
+[[package]]
+name = "axum"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "021e862c184ae977658b36c4500f7feac3221ca5da43e3f25bd04ab6c79a29b5"
+dependencies = [
+ "axum-core 0.5.2",
+ "bytes",
+ "form_urlencoded",
+ "futures-util",
+ "http 1.3.1",
+ "http-body 1.0.1",
+ "http-body-util",
  "hyper 1.6.0",
  "hyper-util",
  "itoa",
- "matchit",
+ "matchit 0.8.4",
  "memchr",
  "mime",
  "percent-encoding",
@@ -721,28 +748,48 @@ dependencies = [
  "sync_wrapper",
  "tower-layer",
  "tower-service",
+]
+
+[[package]]
+name = "axum-core"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68464cd0412f486726fb3373129ef5d2993f90c34bc2bc1c1e9943b2f4fc7ca6"
+dependencies = [
+ "bytes",
+ "futures-core",
+ "http 1.3.1",
+ "http-body 1.0.1",
+ "http-body-util",
+ "mime",
+ "pin-project-lite",
+ "rustversion",
+ "sync_wrapper",
+ "tower-layer",
+ "tower-service",
  "tracing",
 ]
 
 [[package]]
 name = "axum-extra"
-version = "0.9.6"
+version = "0.10.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c794b30c904f0a1c2fb7740f7df7f7972dfaa14ef6f57cb6178dc63e5dca2f04"
+checksum = "45bf463831f5131b7d3c756525b305d40f1185b688565648a92e1392ca35713d"
 dependencies = [
- "axum",
- "axum-core",
+ "axum 0.8.4",
+ "axum-core 0.5.2",
  "bytes",
- "fastrand",
+ "form_urlencoded",
  "futures-util",
  "http 1.3.1",
  "http-body 1.0.1",
  "http-body-util",
  "mime",
- "multer",
  "pin-project-lite",
+ "rustversion",
  "serde",
  "serde_html_form",
+ "serde_path_to_error",
  "tower 0.5.2",
  "tower-layer",
  "tower-service",
@@ -993,7 +1040,7 @@ dependencies = [
 
 [[package]]
 name = "cocoindex"
-version = "0.1.48"
+version = "0.1.50"
 dependencies = [
  "anyhow",
  "async-openai",
@@ -1002,7 +1049,7 @@ dependencies = [
  "aws-config",
  "aws-sdk-s3",
  "aws-sdk-sqs",
- "axum",
+ "axum 0.8.4",
  "axum-extra",
  "base64 0.22.1",
  "blake2",
@@ -1028,6 +1075,7 @@ dependencies = [
  "neo4rs",
  "owo-colors",
  "pgvector",
+ "phf",
  "pyo3",
  "pyo3-async-runtimes",
  "pythonize",
@@ -2610,6 +2658,12 @@ version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0e7465ac9959cc2b1404e8e2367b43684a6d13790fe23056cc8c6c5a6b7bcb94"
 
+[[package]]
+name = "matchit"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "47e1ffaa40ddd1f3ed91f717a33c8c0ee23fff369e3aa8772b9605cc1d22f4c3"
+
 [[package]]
 name = "md-5"
 version = "0.10.6"
@@ -2677,23 +2731,6 @@ dependencies = [
  "windows-sys 0.52.0",
 ]
 
-[[package]]
-name = "multer"
-version = "3.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "83e87776546dc87511aa5ee218730c92b666d7264ab6ed41f9d215af9cd5224b"
-dependencies = [
- "bytes",
- "encoding_rs",
- "futures-util",
- "http 1.3.1",
- "httparse",
- "memchr",
- "mime",
- "spin",
- "version_check",
-]
-
 [[package]]
 name = "neo4rs"
 version = "0.8.0"
@@ -2993,6 +3030,7 @@ version = "0.11.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1fd6780a80ae0c52cc120a26a1a42c1ae51b247a253e4e06113d23d2c2edd078"
 dependencies = [
+ "phf_macros",
  "phf_shared",
 ]
 
@@ -3016,6 +3054,19 @@ dependencies = [
  "rand 0.8.5",
 ]
 
+[[package]]
+name = "phf_macros"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f84ac04429c13a7ff43785d75ad27569f2951ce0ffd30a3321230db2fc727216"
+dependencies = [
+ "phf_generator",
+ "phf_shared",
+ "proc-macro2",
+ "quote",
+ "syn 2.0.101",
+]
+
 [[package]]
 name = "phf_shared"
 version = "0.11.3"
@@ -4653,7 +4704,7 @@ checksum = "877c5b330756d856ffcc4553ab34a5684481ade925ecc54bcd1bf02b1d0d4d52"
 dependencies = [
  "async-stream",
  "async-trait",
- "axum",
+ "axum 0.7.9",
  "base64 0.22.1",
  "bytes",
  "flate2",

{cocoindex-0.1.48 → cocoindex-0.1.50}/Cargo.toml

@@ -2,7 +2,7 @@
 name = "cocoindex"
 # Version used for local development is always higher than others to take precedence.
 # Will be overridden for specific release versions.
-version = "0.1.48"
+version = "0.1.50"
 edition = "2024"
 
 [profile.release]
@@ -20,8 +20,8 @@ pyo3-async-runtimes = { version = "0.24.0", features = ["tokio-runtime"] }
 
 anyhow = { version = "1.0.97", features = ["std"] }
 async-trait = "0.1.88"
-axum = "0.7.9"
-axum-extra = { version = "0.9.6", features = ["query"] }
+axum = "0.8.4"
+axum-extra = { version = "0.10.1", features = ["query"] }
 base64 = "0.22.1"
 chrono = "0.4.40"
 config = "0.14.1"
@@ -50,6 +50,7 @@ tower-http = { version = "0.6.2", features = ["cors", "trace"] }
 indexmap = { version = "2.8.0", features = ["serde"] }
 blake2 = "0.10.6"
 pgvector = { version = "0.4.0", features = ["sqlx"] }
+phf = { version = "0.11.3", features = ["macros"] }
 indenter = "0.3.3"
 itertools = "0.14.0"
 derivative = "2.2.0"

{cocoindex-0.1.48 → cocoindex-0.1.50}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.48
+Version: 0.1.50
 Requires-Dist: sentence-transformers>=3.3.1
 Requires-Dist: click>=8.1.8
 Requires-Dist: rich>=14.0.0

{cocoindex-0.1.48 → cocoindex-0.1.50}/docs/docs/core/data_types.mdx

@@ -36,16 +36,17 @@ This is the list of all basic types supported by CocoIndex:
 | LocalDatetime | Date and time without timezone | `cocoindex.LocalDateTime` | `datetime.datetime` |
 | OffsetDatetime | Date and time with a timezone offset | `cocoindex.OffsetDateTime` | `datetime.datetime` |
 | TimeDelta | A duration of time | `datetime.timedelta` | `datetime.timedelta` |
-| Vector[*T*, *Dim*?] | *T* must be basic type. *Dim* is a positive integer and optional. |`cocoindex.Vector[T]` or `cocoindex.Vector[T, Dim]` | `list[T]` | 
 | Json | | `cocoindex.Json` | Any data convertible to JSON by `json` package | 
+| Vector[*T*, *Dim*?] | *T* can be a basic type or a numeric type. *Dim* is a positive integer and optional. | `cocoindex.Vector[T]` or `cocoindex.Vector[T, Dim]` | `numpy.typing.NDArray[T]` or `list[T]` |
 
 Values of all data types can be represented by values in Python's native types (as described under the Native Python Type column).
 However, the underlying execution engine and some storage system (like Postgres) has finer distinctions for some types, specifically:
 
 *   *Float32* and *Float64* for `float`, with different precision.
 *   *LocalDateTime* and *OffsetDateTime* for `datetime.datetime`, with different timezone awareness.
-*   *Vector* has optional dimension information.
 *   *Range* and *Json* provide a clear tag for the type, to clearly distinguish the type in CocoIndex.
+*   *Vector* holds elements of type *T*. If *T* is numeric (e.g., `np.float32` or `np.float64`), it's represented as `NDArray[T]`; otherwise, as `list[T]`.
+*   *Vector* also has optional dimension information.
 
 The native Python type is always more permissive and can represent a superset of possible values.
 *   Only when you annotate the return type of a custom function, you should use the specific type,

cocoindex-0.1.50/docs/docs/getting_started/overview.md

@@ -0,0 +1,36 @@
+---
+title: Overview
+slug: /
+---
+
+# Welcome to CocoIndex
+
+CocoIndex is an ultra-performant real-time data transformation framework for AI, with incremental processing. 
+
+As a data framework, CocoIndex takes it to the next level on data freshness. **Incremental processing** is one of the core values provided by CocoIndex.
+
+![Incremental Processing](/img/incremental-etl.gif)
+
+## Programming Model
+CocoIndex follows the idea of [Dataflow programming](https://en.wikipedia.org/wiki/Dataflow_programming) model. Each transformation creates a new field solely based on input fields, without hidden states and value mutation. All data before/after each transformation is observable, with lineage out of the box.
+
+The gist of an example data transformation:
+```python
+# import
+data['content'] = flow_builder.add_source(...) 
+
+# transform
+data['out'] = data['content'] 
+    .transform(...)
+    .transform(...)
+
+# collect data
+collector.collect(...)
+
+# export to db, vector db, graph db ...
+collector.export(...)
+```
+
+Get Started:
+- [Quick Start](https://cocoindex.io/docs/getting_started/quickstart)
+

{cocoindex-0.1.48 → cocoindex-0.1.50}/docs/docs/getting_started/quickstart.md

@@ -154,11 +154,11 @@ The goal of transforming your data is usually to query against it.
 Once you already have your index built, you can directly access the transformed data in the target database.
 CocoIndex also provides utilities for you to do this more seamlessly.
 
-In this example, we'll use the [`psycopg` library](https://www.psycopg.org/) to connect to the database and run queries.
-Please make sure it's installed:
+In this example, we'll use the [`psycopg` library](https://www.psycopg.org/) along with pgvector to connect to the database and run queries on vector data.
+Please make sure the required packages are installed:
 
 ```bash
-pip install psycopg[binary,pool]
+pip install numpy psycopg[binary,pool] pgvector
 ```
 
 ### Step 4.1: Extract common transformations
@@ -169,8 +169,11 @@ i.e. they should use exactly the same embedding model and parameters.
 Let's extract that into a function:
 
 ```python title="quickstart.py"
+from numpy.typing import NDArray
+import numpy as np
+
 @cocoindex.transform_flow()
-def text_to_embedding(text: cocoindex.DataSlice[str]) -> cocoindex.DataSlice[list[float]]:
+def text_to_embedding(text: cocoindex.DataSlice[str]) -> cocoindex.DataSlice[NDArray[np.float32]]:
     return text.transform(
         cocoindex.functions.SentenceTransformerEmbed(
             model="sentence-transformers/all-MiniLM-L6-v2"))
@@ -207,6 +210,7 @@ Now we can create a function to query the index upon a given input query:
 
 ```python title="quickstart.py"
 from psycopg_pool import ConnectionPool
+from pgvector.psycopg import register_vector
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the text_embedding_flow above.
@@ -215,9 +219,10 @@ def search(pool: ConnectionPool, query: str, top_k: int = 5):
     query_vector = text_to_embedding.eval(query)
     # Run the query and get the results.
     with pool.connection() as conn:
+        register_vector(conn)
         with conn.cursor() as cur:
             cur.execute(f"""
-                SELECT filename, text, embedding <=> %s::vector AS distance
+                SELECT filename, text, embedding <=> %s AS distance
                 FROM {table_name} ORDER BY distance LIMIT %s
             """, (query_vector, top_k))
             return [
@@ -236,7 +241,7 @@ There're two CocoIndex-specific logic:
 
 2.  Evaluate the transform flow defined above with the input query, to get the embedding.
     It's done by the `eval()` method of the transform flow `text_to_embedding`.
-    The return type of this method is `list[float]` as declared in the `text_to_embedding()` function (`cocoindex.DataSlice[list[float]]`).
+    The return type of this method is `NDArray[np.float32]` as declared in the `text_to_embedding()` function (`cocoindex.DataSlice[NDArray[np.float32]]`).
 
 ### Step 4.3: Add the main script logic
 

{cocoindex-0.1.48 → cocoindex-0.1.50}/docs/docs/ops/functions.md

@@ -39,9 +39,27 @@ Input data:
 
 *   `chunk_overlap` (type: `int`, optional): The maximum overlap size between adjacent chunks, in bytes.
 *   `language` (type: `str`, optional): The language of the document.
-    Can be a langauge name (e.g. `Python`, `Javascript`, `Markdown`) or a file extension (e.g. `.py`, `.js`, `.md`).
-    To see all supported language names and extensions, see [the code](https://github.com/search?q=org%3Acocoindex-io+lang%3Arust++%22static+TREE_SITTER_LANGUAGE_BY_LANG%22&type=code).
-    If it's unspecified or the specified language is not supported, it will be treated as plain text.
+    Can be a language name (e.g. `Python`, `Javascript`, `Markdown`) or a file extension (e.g. `.py`, `.js`, `.md`).
+
+*   `custom_languages` (type: `list[CustomLanguageSpec]`, optional): This allows you to customize the way to chunking specific languages using regular expressions. Each `CustomLanguageSpec` is a dict with the following fields:
+    *   `language_name` (type: `str`, required): Name of the language.
+    *   `aliases` (type: `list[str]`, optional): A list of aliases for the language.
+        It's an error if any language name or alias is duplicated.
+
+    *   `separators_regex` (type: `list[str]`, required): A list of regex patterns to split the text.
+        Higher-level boundaries should come first, and lower-level should be listed later. e.g. `[r"\n# ", r"\n## ", r"\n\n", r"\. "]`.
+        See [regex Syntax](https://docs.rs/regex/latest/regex/#syntax) for supported regular expression syntax.
+
+    :::note
+
+    We use the `language` field to determine how to split the input text, following these rules:
+    
+    *   We'll match the input `language` field against the `language_name` or `aliases` of each custom language specification, and use the matched one. If value of `language` is null, it'll be treated as empty string when matching `language_name` or `aliases`.
+    *   If no match is found, we'll match the `language` field against the builtin language configurations.
+        For all supported builtin language names and aliases (extensions), see [the code](https://github.com/search?q=org%3Acocoindex-io+lang%3Arust++%22static+TREE_SITTER_LANGUAGE_BY_LANG%22&type=code).
+    *   If no match is found, the input will be treated as plain text.
+
+    :::
 
 Return type: [KTable](/docs/core/data_types#ktable), each row represents a chunk, with the following sub fields:
 

{cocoindex-0.1.48 → cocoindex-0.1.50}/docs/docs/ops/storages.md

@@ -54,34 +54,21 @@ Here's how CocoIndex data elements map to Qdrant elements during export:
 |-------------------|------------------|
 | an export target  | a unique collection |  
 | a collected row   | a point |
-| a field           | a named vector (for fields with vector type); a field within payload (otherwise) |
+| a field           | a named vector, if fits into Qdrant vector; or a field within payload otherwise |
+
+A vector with `Float32`, `Float64` or `Int64` type, and with fixed dimension, fits into Qdrant vector.
 
 #### Spec
 
 The spec takes the following fields:
 
-*   `collection_name` (type: `str`, required): The name of the collection to export the data to.
-
-*   `grpc_url` (type: `str`, optional): The [gRPC URL](https://qdrant.tech/documentation/interfaces/#grpc-interface) of the Qdrant instance. Defaults to `http://localhost:6334/`.
-
-*   `api_key` (type: `str`, optional). API key to authenticate requests with.
+*   `connection` (type: [auth reference](../core/flow_def#auth-registry) to `QdrantConnection`, optional): The connection to the Qdrant instance. `QdrantConnection` has the following fields:
+    *   `grpc_url` (type: `str`): The [gRPC URL](https://qdrant.tech/documentation/interfaces/#grpc-interface) of the Qdrant instance, e.g. `http://localhost:6334/`.
+    *   `api_key` (type: `str`, optional). API key to authenticate requests with.
 
-Before exporting, you must create a collection with a [vector name](https://qdrant.tech/documentation/concepts/vectors/#named-vectors) that matches the vector field name in CocoIndex, and set `setup_by_user=True` during export.
+    If `connection` is not provided, will use local Qdrant instance at `http://localhost:6334/` by default.
 
-Example:
-
-```python
-doc_embeddings.export(
-    "doc_embeddings",
-    cocoindex.storages.Qdrant(
-        collection_name="cocoindex",
-        grpc_url="https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6334/",
-        api_key="<your-api-key-here>",
-    ),
-    primary_key_fields=["id_field"],
-    setup_by_user=True,
-)
-```
+*   `collection_name` (type: `str`, required): The name of the collection to export the data to.
 
 You can find an end-to-end example [here](https://github.com/cocoindex-io/cocoindex/tree/main/examples/text_embedding_qdrant).
 
@@ -399,19 +386,7 @@ You can find end-to-end examples fitting into any of supported property graphs i
 
 ### Neo4j
 
-If you don't have a Neo4j database, you can start a Neo4j database using our docker compose config:
-
-```bash
-docker compose -f <(curl -L https://raw.githubusercontent.com/cocoindex-io/cocoindex/refs/heads/main/dev/neo4j.yaml) up -d
-```
-
-:::warning
-
-The docker compose config above will start a Neo4j Enterprise instance under the [Evaluation License](https://neo4j.com/terms/enterprise_us/),
-with 30 days trial period.
-Please read and agree the license before starting the instance.
-
-:::
+#### Spec
 
 The `Neo4j` target spec takes the following fields:
 
@@ -430,17 +405,32 @@ Neo4j also provides a declaration spec `Neo4jDeclaration`, to configure indexing
     *   `primary_key_fields` (required)
     *   `vector_indexes` (optional)
 
-### Kuzu
+#### Neo4j dev instance
 
-CocoIndex supports talking to Kuzu through its [API server](https://github.com/kuzudb/api-server).
-You can bring up a Kuzu API server locally by running:
+If you don't have a Neo4j database, you can start a Neo4j database using our docker compose config:
 
 ```bash
-KUZU_DB_DIR=$HOME/.kuzudb
-KUZU_PORT=8123
-docker run -d --name kuzu -p ${KUZU_PORT}:8000 -v ${KUZU_DB_DIR}:/database kuzudb/api-server:latest
+docker compose -f <(curl -L https://raw.githubusercontent.com/cocoindex-io/cocoindex/refs/heads/main/dev/neo4j.yaml) up -d
 ```
 
+If will bring up a Neo4j instance, which can be accessed by username `neo4j` and password `cocoindex`.
+You can access the Neo4j browser at [http://localhost:7474](http://localhost:7474).
+
+:::warning
+
+The docker compose config above will start a Neo4j Enterprise instance under the [Evaluation License](https://neo4j.com/terms/enterprise_us/),
+with 30 days trial period.
+Please read and agree the license before starting the instance.
+
+:::
+
+
+### Kuzu
+
+#### Spec
+
+CocoIndex supports talking to Kuzu through its [API server](https://github.com/kuzudb/api-server).
+
 The `Kuzu` target spec takes the following fields:
 
 *   `connection` (type: [auth reference](../core/flow_def#auth-registry) to `KuzuConnectionSpec`): The connection to the Kuzu database. `KuzuConnectionSpec` has the following fields:
@@ -453,3 +443,25 @@ Kuzu also provides a declaration spec `KuzuDeclaration`, to configure indexing o
 *   Fields for [nodes to declare](#declare-extra-node-labels), including
     *   `nodes_label` (required)
     *   `primary_key_fields` (required)
+
+#### Kuzu dev instance
+
+If you don't have a Kuzu instance yet, you can bring up a Kuzu API server locally by running:
+
+```bash
+KUZU_DB_DIR=$HOME/.kuzudb
+KUZU_PORT=8123
+docker run -d --name kuzu -p ${KUZU_PORT}:8000 -v ${KUZU_DB_DIR}:/database kuzudb/api-server:latest
+```
+
+To explore the graph you built with Kuzu, you can use the [Kuzu Explorer](https://github.com/kuzudb/explorer).
+Currently Kuzu API server and the explorer cannot be up at the same time. So you need to stop the API server before running the explorer.
+
+To start the instance of the explorer, run:
+
+```bash
+KUZU_EXPLORER_PORT=8124
+docker run -d --name kuzu-explorer -p ${KUZU_EXPLORER_PORT}:8000  -v ${KUZU_DB_DIR}:/database -e MODE=READ_ONLY  kuzudb/explorer:latest
+```
+
+You can then access the explorer at [http://localhost:8124](http://localhost:8124).

{cocoindex-0.1.48 → cocoindex-0.1.50}/docs/docs/query.mdx

@@ -41,7 +41,7 @@ The [quickstart](getting_started/quickstart#step-41-extract-common-transformatio
 
 ```python
 @cocoindex.transform_flow()
-def text_to_embedding(text: cocoindex.DataSlice[str]) -> cocoindex.DataSlice[list[float]]:
+def text_to_embedding(text: cocoindex.DataSlice[str]) -> cocoindex.DataSlice[NDArray[np.float32]]:
     return text.transform(
         cocoindex.functions.SentenceTransformerEmbed(
             model="sentence-transformers/all-MiniLM-L6-v2"))
@@ -61,7 +61,7 @@ with doc["chunks"].row() as chunk:
     chunk["embedding"] = chunk["text"].call(text_to_embedding)
 ```
 
-Any time, you can call the `eval()` method with specific string, which will return a `list[float]`:
+Any time, you can call the `eval()` method with specific string, which will return a `NDArray[np.float32]`:
 
 ```python
 print(text_to_embedding.eval("Hello, world!"))
@@ -93,7 +93,7 @@ For example:
 
 ```python
 table_name = cocoindex.utils.get_target_storage_default_name(text_embedding_flow, "doc_embeddings")
-query = f"SELECT filename, text FROM {table_name} ORDER BY embedding <=> %s::vector DESC LIMIT 5"
+query = f"SELECT filename, text FROM {table_name} ORDER BY embedding <=> %s DESC LIMIT 5"
 ...
 ```
 

{cocoindex-0.1.48 → cocoindex-0.1.50}/examples/docs_to_knowledge_graph/README.md

@@ -12,10 +12,10 @@ Please drop [Cocoindex on Github](https://github.com/cocoindex-io/cocoindex) a s
 
 ![example-explanation](https://github.com/user-attachments/assets/07ddbd60-106f-427f-b7cc-16b73b142d27)
 
-
 ## Prerequisite
 *   [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
-*   [Install Neo4j](https://cocoindex.io/docs/ops/storages#neo4j) if you don't have one.
+*   Install [Neo4j](https://cocoindex.io/docs/ops/storages#neo4j-dev-instance) or [Kuzu](https://cocoindex.io/docs/ops/storages#kuzu-dev-instance) if you don't have one.
+    *   The example uses Neo4j by default for now. If you want to use Kuzu, find out the "SELECT ONE GRAPH DATABASE TO USE" section and switch the active branch.
 *   [Configure your OpenAI API key](https://cocoindex.io/docs/ai/llm#openai).
 
 ## Documentation
@@ -45,21 +45,18 @@ cocoindex update main.py
 
 ### Browse the knowledge graph
 
-After the knowledge graph is build, you can explore the knowledge graph you built in Neo4j Browser.
+After the knowledge graph is built, you can explore the knowledge graph.
 
-For the dev enviroment, you can connect neo4j browser using credentials:
-- username: `neo4j`
-- password: `cocoindex`
-which is pre-configured in the our docker compose [config.yaml](https://raw.githubusercontent.com/cocoindex-io/cocoindex/refs/heads/main/dev/neo4j.yaml).
+* If you're using Neo4j, you can open the explorer at [http://localhost:7474](http://localhost:7474), with username `neo4j` and password `cocoindex`.
+* If you're using Kuzu, you can start a Kuzu explorer locally. See [Kuzu dev instance](https://cocoindex.io/docs/ops/storages#kuzu-dev-instance) for more details.
 
-You can open it at [http://localhost:7474](http://localhost:7474), and run the following Cypher query to get all relationships:
+You can run the following Cypher query to get all relationships:
 
 ```cypher
 MATCH p=()-->() RETURN p
 ```
-<img width="1366" alt="neo4j-for-coco-docs" src="https://github.com/user-attachments/assets/3c8b6329-6fee-4533-9480-571399b57e57" />
-
 
+<img width="1366" alt="neo4j-for-coco-docs" src="https://github.com/user-attachments/assets/3c8b6329-6fee-4533-9480-571399b57e57" />
 
 ## CocoInsight 
 I used CocoInsight (Free beta now) to troubleshoot the index generation and understand the data lineage of the pipeline. 

{cocoindex-0.1.48 → cocoindex-0.1.50}/examples/docs_to_knowledge_graph/main.py

@@ -5,27 +5,6 @@ This example shows how to extract relationships from documents and build a knowl
 import dataclasses
 import cocoindex
 
-
-@dataclasses.dataclass
-class DocumentSummary:
-    """Describe a summary of a document."""
-
-    title: str
-    summary: str
-
-
-@dataclasses.dataclass
-class Relationship:
-    """
-    Describe a relationship between two entities.
-    Subject and object should be Core CocoIndex concepts only, should be nouns. For example, `CocoIndex`, `Incremental Processing`, `ETL`,  `Data` etc.
-    """
-
-    subject: str
-    predicate: str
-    object: str
-
-
 neo4j_conn_spec = cocoindex.add_auth_entry(
     "Neo4jConnection",
     cocoindex.storages.Neo4jConnection(
@@ -41,19 +20,43 @@ kuzu_conn_spec = cocoindex.add_auth_entry(
     ),
 )
 
-# Use Neo4j as the graph database
+# SELECT ONE GRAPH DATABASE TO USE
+# This example can use either Neo4j or Kuzu as the graph database.
+# Please make sure only one branch is live and others are commented out.
+
+# Use Neo4j
 GraphDbSpec = cocoindex.storages.Neo4j
 GraphDbConnection = cocoindex.storages.Neo4jConnection
 GraphDbDeclaration = cocoindex.storages.Neo4jDeclaration
 conn_spec = neo4j_conn_spec
 
-# Use Kuzu as the graph database
+# Use Kuzu
 #  GraphDbSpec = cocoindex.storages.Kuzu
 #  GraphDbConnection = cocoindex.storages.KuzuConnection
 #  GraphDbDeclaration = cocoindex.storages.KuzuDeclaration
 #  conn_spec = kuzu_conn_spec
 
 
+@dataclasses.dataclass
+class DocumentSummary:
+    """Describe a summary of a document."""
+
+    title: str
+    summary: str
+
+
+@dataclasses.dataclass
+class Relationship:
+    """
+    Describe a relationship between two entities.
+    Subject and object should be Core CocoIndex concepts only, should be nouns. For example, `CocoIndex`, `Incremental Processing`, `ETL`,  `Data` etc.
+    """
+
+    subject: str
+    predicate: str
+    object: str
+
+
 @cocoindex.flow_def(name="DocsToKG")
 def docs_to_kg_flow(
     flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope