From 2b74fccadb87701eff91bf4ce315829fc3fd9e62 Mon Sep 17 00:00:00 2001
From: Sourabh Desai <sourabhdesai@gmail.com>
Date: Sat, 20 Jan 2024 19:46:12 -0800
Subject: [PATCH] make hash a @property (#10163)
* make hash a @property
* fix tests by making hash property a required abstractmethod on basenode
* update changelog
---
CHANGELOG.md | 1 +
llama_index/schema.py | 22 ++++++++++------------
2 files changed, 11 insertions(+), 12 deletions(-)
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 40fef716dc..6a85d218d3 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,7 @@
### New Features
- `beautifulsoup4` dependency to new optional extra `html` (#10156)
+- make `BaseNode.hash` an `@property` (#10163)
## [0.9.34] - 2024-01-19
diff --git a/llama_index/schema.py b/llama_index/schema.py
index 7647045236..e3382bae13 100644
--- a/llama_index/schema.py
+++ b/llama_index/schema.py
@@ -12,7 +12,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional, Union
from dataclasses_json import DataClassJsonMixin
from typing_extensions import Self
-from llama_index.bridge.pydantic import BaseModel, Field, root_validator
+from llama_index.bridge.pydantic import BaseModel, Field
from llama_index.utils import SAMPLE_TEXT, truncate_text
if TYPE_CHECKING:
@@ -223,7 +223,6 @@ class BaseNode(BaseComponent):
default_factory=dict,
description="A mapping of relationships to other node information.",
)
- hash: str = Field(default="", description="Hash of the node content.")
@classmethod
@abstractmethod
@@ -242,6 +241,11 @@ class BaseNode(BaseComponent):
def set_content(self, value: Any) -> None:
"""Set the content of the node."""
+ @property
+ @abstractmethod
+ def hash(self) -> str:
+ """Get hash of node."""
+
@property
def node_id(self) -> str:
return self.id_
@@ -382,16 +386,10 @@ class TextNode(BaseNode):
def class_name(cls) -> str:
return "TextNode"
- @root_validator
- def _check_hash(cls, values: dict) -> dict:
- """Generate a hash to represent the node."""
- text = values.get("text", "")
- metadata = values.get("metadata", {})
- doc_identity = str(text) + str(metadata)
- values["hash"] = str(
- sha256(doc_identity.encode("utf-8", "surrogatepass")).hexdigest()
- )
- return values
+ @property
+ def hash(self) -> str:
+ doc_identity = str(self.text) + str(self.metadata)
+ return str(sha256(doc_identity.encode("utf-8", "surrogatepass")).hexdigest())
@classmethod
def get_type(cls) -> str:
--
GitLab