LightRAG
1.0.0
يستضيف هذا المستودع رمز Lightrag. يعتمد هيكل هذا الرمز على nano-graphrag.
textract . الشكل 1: مخطط انسياب فهرسة Lightrag الشكل 2: استرجاع Lightrag والاستعلام
cd LightRAG
pip install -e .pip install lightrag-hkuexamples .export OPENAI_API_KEY="sk-...".curl https://raw.githubusercontent.com/gusye1234/nano-graphrag/main/tests/mock_data.txt > ./book.txtاستخدم مقتطف Python أدناه (في البرنامج النصي) لتهيئة Lightrag وأداء الاستعلامات:
import os
from lightrag import LightRAG , QueryParam
from lightrag . llm import gpt_4o_mini_complete , gpt_4o_complete
#########
# Uncomment the below two lines if running in a jupyter notebook to handle the async nature of rag.insert()
# import nest_asyncio
# nest_asyncio.apply()
#########
WORKING_DIR = "./dickens"
if not os . path . exists ( WORKING_DIR ):
os . mkdir ( WORKING_DIR )
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = gpt_4o_mini_complete # Use gpt_4o_mini_complete LLM model
# llm_model_func=gpt_4o_complete # Optionally, use a stronger model
)
with open ( "./book.txt" ) as f :
rag . insert ( f . read ())
# Perform naive search
print ( rag . query ( "What are the top themes in this story?" , param = QueryParam ( mode = "naive" )))
# Perform local search
print ( rag . query ( "What are the top themes in this story?" , param = QueryParam ( mode = "local" )))
# Perform global search
print ( rag . query ( "What are the top themes in this story?" , param = QueryParam ( mode = "global" )))
# Perform hybrid search
print ( rag . query ( "What are the top themes in this story?" , param = QueryParam ( mode = "hybrid" ))) async def llm_model_func (
prompt , system_prompt = None , history_messages = [], ** kwargs
) -> str :
return await openai_complete_if_cache (
"solar-mini" ,
prompt ,
system_prompt = system_prompt ,
history_messages = history_messages ,
api_key = os . getenv ( "UPSTAGE_API_KEY" ),
base_url = "https://api.upstage.ai/v1/solar" ,
** kwargs
)
async def embedding_func ( texts : list [ str ]) -> np . ndarray :
return await openai_embedding (
texts ,
model = "solar-embedding-1-large-query" ,
api_key = os . getenv ( "UPSTAGE_API_KEY" ),
base_url = "https://api.upstage.ai/v1/solar"
)
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = llm_model_func ,
embedding_func = EmbeddingFunc (
embedding_dim = 4096 ,
max_token_size = 8192 ,
func = embedding_func
)
) from lightrag . llm import hf_model_complete , hf_embedding
from transformers import AutoModel , AutoTokenizer
from lightrag . utils import EmbeddingFunc
# Initialize LightRAG with Hugging Face model
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = hf_model_complete , # Use Hugging Face model for text generation
llm_model_name = 'meta-llama/Llama-3.1-8B-Instruct' , # Model name from Hugging Face
# Use Hugging Face embedding function
embedding_func = EmbeddingFunc (
embedding_dim = 384 ,
max_token_size = 5000 ,
func = lambda texts : hf_embedding (
texts ,
tokenizer = AutoTokenizer . from_pretrained ( "sentence-transformers/all-MiniLM-L6-v2" ),
embed_model = AutoModel . from_pretrained ( "sentence-transformers/all-MiniLM-L6-v2" )
)
),
) إذا كنت ترغب في استخدام نماذج Ollama ، فأنت بحاجة إلى سحب النموذج الذي تخطط لاستخدامه وتضمين النموذج ، على سبيل المثال nomic-embed-text .
ثم تحتاج فقط إلى ضبط lightrag على النحو التالي:
from lightrag . llm import ollama_model_complete , ollama_embedding
from lightrag . utils import EmbeddingFunc
# Initialize LightRAG with Ollama model
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = ollama_model_complete , # Use Ollama model for text generation
llm_model_name = 'your_model_name' , # Your model name
# Use Ollama embedding function
embedding_func = EmbeddingFunc (
embedding_dim = 768 ,
max_token_size = 8192 ,
func = lambda texts : ollama_embedding (
texts ,
embed_model = "nomic-embed-text"
)
),
) export NEO4J_URI = "neo4j://localhost:7687"
export NEO4J_USERNAME = "neo4j"
export NEO4J_PASSWORD = "password"
When you launch the project be sure to override the default KG : NetworkS
by specifying kg = "Neo4JStorage" .
# Note: Default settings use NetworkX
#Initialize LightRAG with Neo4J implementation.
WORKING_DIR = "./local_neo4jWorkDir"
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = gpt_4o_mini_complete , # Use gpt_4o_mini_complete LLM model
kg = "Neo4JStorage" , #<-----------override KG default
log_level = "DEBUG" #<-----------override log_level default
)انظر test_neo4j.py للحصول على مثال عمل.
من أجل أن يكون سياق Lightrag أن يكون ما لا يقل عن 32 ألف رمز. بشكل افتراضي ، فإن نماذج Ollama لها حجم سياق 8K. يمكنك تحقيق ذلك باستخدام واحدة من طريقتين:
num_ctx في modelfile.ollama pull qwen2ollama show --modelfile qwen2 > ModelfilePARAMETER num_ctx 32768ollama create -f Modelfile qwen2mnum_ctx عبر Ollama API. يمكن TIY استخدام llm_model_kwargs PARAN لتكوين Ollama:
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = ollama_model_complete , # Use Ollama model for text generation
llm_model_name = 'your_model_name' , # Your model name
llm_model_kwargs = { "options" : { "num_ctx" : 32768 }},
# Use Ollama embedding function
embedding_func = EmbeddingFunc (
embedding_dim = 768 ,
max_token_size = 8192 ,
func = lambda texts : ollama_embedding (
texts ,
embed_model = "nomic-embed-text"
)
),
) هناك examples/lightrag_ollama_demo.py التي تستخدم نموذج gemma2:2b ، تعمل فقط 4 طلبات بالتوازي وتعيين حجم السياق إلى 32 كيلو بايت.
من أجل تشغيل هذه التجربة على GPU منخفضة ذاكرة الوصول العشوائي ، يجب عليك تحديد نافذة سياق النموذج الصغير (زيادة السياق زيادة استهلاك الذاكرة). على سبيل المثال ، تشغيل مثال Ollama على وحدة معالجة الرسومات التعدين المعاد تشغيلها مع 6 جيجابايت من ذاكرة الوصول العشوائي المطلوبة لتعيين حجم السياق على 26K أثناء استخدام gemma2:2b . تمكنت من العثور على 197 كيانًا و 19 علاقات على book.txt .
class QueryParam :
mode : Literal [ "local" , "global" , "hybrid" , "naive" ] = "global"
only_need_context : bool = False
response_type : str = "Multiple Paragraphs"
# Number of top-k items to retrieve; corresponds to entities in "local" mode and relationships in "global" mode.
top_k : int = 60
# Number of tokens for the original chunks.
max_token_for_text_unit : int = 4000
# Number of tokens for the relationship descriptions
max_token_for_global_context : int = 4000
# Number of tokens for the entity descriptions
max_token_for_local_context : int = 4000 # Batch Insert: Insert multiple texts at once
rag . insert ([ "TEXT1" , "TEXT2" ,...]) # Incremental Insert: Insert new documents into an existing LightRAG instance
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = llm_model_func ,
embedding_func = EmbeddingFunc (
embedding_dim = embedding_dimension ,
max_token_size = 8192 ,
func = embedding_func ,
),
)
with open ( "./newText.txt" ) as f :
rag . insert ( f . read ()) rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = llm_model_func ,
embedding_func = EmbeddingFunc (
embedding_dim = embedding_dimension ,
max_token_size = 8192 ,
func = embedding_func ,
),
)
custom_kg = {
"entities" : [
{
"entity_name" : "CompanyA" ,
"entity_type" : "Organization" ,
"description" : "A major technology company" ,
"source_id" : "Source1"
},
{
"entity_name" : "ProductX" ,
"entity_type" : "Product" ,
"description" : "A popular product developed by CompanyA" ,
"source_id" : "Source1"
}
],
"relationships" : [
{
"src_id" : "CompanyA" ,
"tgt_id" : "ProductX" ,
"description" : "CompanyA develops ProductX" ,
"keywords" : "develop, produce" ,
"weight" : 1.0 ,
"source_id" : "Source1"
}
]
}
rag . insert_custom_kg ( custom_kg ) # Delete Entity: Deleting entities by their names
rag = LightRAG (
working_dir = WORKING_DIR ,
llm_model_func = llm_model_func ,
embedding_func = EmbeddingFunc (
embedding_dim = embedding_dimension ,
max_token_size = 8192 ,
func = embedding_func ,
),
)
rag . delete_by_entity ( "Project Gutenberg" ) يدعم textract أنواع الملفات القراءة مثل TXT و DOCX و PPTX و CSV و PDF.
import textract
file_path = 'TEXT.pdf'
text_content = textract . process ( file_path )
rag . insert ( text_content . decode ( 'utf-8' ))examples/graph_visual_with_html.py import networkx as nx
from pyvis . network import Network
# Load the GraphML file
G = nx . read_graphml ( './dickens/graph_chunk_entity_relation.graphml' )
# Create a Pyvis network
net = Network ( notebook = True )
# Convert NetworkX graph to Pyvis network
net . from_nx ( G )
# Save and display the network
net . show ( 'knowledge_graph.html' )examples/graph_visual_with_neo4j.py import os
import json
from lightrag . utils import xml_to_json
from neo4j import GraphDatabase
# Constants
WORKING_DIR = "./dickens"
BATCH_SIZE_NODES = 500
BATCH_SIZE_EDGES = 100
# Neo4j connection credentials
NEO4J_URI = "bolt://localhost:7687"
NEO4J_USERNAME = "neo4j"
NEO4J_PASSWORD = "your_password"
def convert_xml_to_json ( xml_path , output_path ):
"""Converts XML file to JSON and saves the output."""
if not os . path . exists ( xml_path ):
print ( f"Error: File not found - { xml_path } " )
return None
json_data = xml_to_json ( xml_path )
if json_data :
with open ( output_path , 'w' , encoding = 'utf-8' ) as f :
json . dump ( json_data , f , ensure_ascii = False , indent = 2 )
print ( f"JSON file created: { output_path } " )
return json_data
else :
print ( "Failed to create JSON data" )
return None
def process_in_batches ( tx , query , data , batch_size ):
"""Process data in batches and execute the given query."""
for i in range ( 0 , len ( data ), batch_size ):
batch = data [ i : i + batch_size ]
tx . run ( query , { "nodes" : batch } if "nodes" in query else { "edges" : batch })
def main ():
# Paths
xml_file = os . path . join ( WORKING_DIR , 'graph_chunk_entity_relation.graphml' )
json_file = os . path . join ( WORKING_DIR , 'graph_data.json' )
# Convert XML to JSON
json_data = convert_xml_to_json ( xml_file , json_file )
if json_data is None :
return
# Load nodes and edges
nodes = json_data . get ( 'nodes' , [])
edges = json_data . get ( 'edges' , [])
# Neo4j queries
create_nodes_query = """
UNWIND $nodes AS node
MERGE (e:Entity {id: node.id})
SET e.entity_type = node.entity_type,
e.description = node.description,
e.source_id = node.source_id,
e.displayName = node.id
REMOVE e:Entity
WITH e, node
CALL apoc.create.addLabels(e, [node.entity_type]) YIELD node AS labeledNode
RETURN count(*)
"""
create_edges_query = """
UNWIND $edges AS edge
MATCH (source {id: edge.source})
MATCH (target {id: edge.target})
WITH source, target, edge,
CASE
WHEN edge.keywords CONTAINS 'lead' THEN 'lead'
WHEN edge.keywords CONTAINS 'participate' THEN 'participate'
WHEN edge.keywords CONTAINS 'uses' THEN 'uses'
WHEN edge.keywords CONTAINS 'located' THEN 'located'
WHEN edge.keywords CONTAINS 'occurs' THEN 'occurs'
ELSE REPLACE(SPLIT(edge.keywords, ',')[0], ' " ', '')
END AS relType
CALL apoc.create.relationship(source, relType, {
weight: edge.weight,
description: edge.description,
keywords: edge.keywords,
source_id: edge.source_id
}, target) YIELD rel
RETURN count(*)
"""
set_displayname_and_labels_query = """
MATCH (n)
SET n.displayName = n.id
WITH n
CALL apoc.create.setLabels(n, [n.entity_type]) YIELD node
RETURN count(*)
"""
# Create a Neo4j driver
driver = GraphDatabase . driver ( NEO4J_URI , auth = ( NEO4J_USERNAME , NEO4J_PASSWORD ))
try :
# Execute queries in batches
with driver . session () as session :
# Insert nodes in batches
session . execute_write ( process_in_batches , create_nodes_query , nodes , BATCH_SIZE_NODES )
# Insert edges in batches
session . execute_write ( process_in_batches , create_edges_query , edges , BATCH_SIZE_EDGES )
# Set displayName and labels
session . run ( set_displayname_and_labels_query )
except Exception as e :
print ( f"Error occurred: { e } " )
finally :
driver . close ()
if __name__ == "__main__" :
main ()| المعلمة | يكتب | توضيح | تقصير |
|---|---|---|---|
| work_dir | str | دليل حيث سيتم تخزين ذاكرة التخزين المؤقت | lightrag_cache+timestamp |
| kv_storage | str | نوع التخزين للمستندات وقطع النص. الأنواع المدعومة: JsonKVStorage ، OracleKVStorage | JsonKVStorage |
| Vector_Storage | str | نوع التخزين لتضمين المتجهات. الأنواع المدعومة: NanoVectorDBStorage ، OracleVectorDBStorage | NanoVectorDBStorage |
| graph_storage | str | نوع التخزين لحواف الرسم البياني والعقد. الأنواع المدعومة: NetworkXStorage ، Neo4JStorage ، OracleGraphStorage | NetworkXStorage |
| log_level | مستوى السجل لوقت تشغيل التطبيق | logging.DEBUG | |
| chunk_token_size | int | الحد الأقصى لحجم الرمز المميز لكل قطعة عند تقسيم المستندات | 1200 |
| chunk_overlap_token_size | int | يتداخل حجم الرمز المميز بين قطعتين عند تقسيم المستندات | 100 |
| tiktoken_model_name | str | اسم النموذج لمشفر Tiktoken المستخدم لحساب أرقام الرمز المميز | gpt-4o-mini |
| entity_extract_max_gleaning | int | عدد الحلقات في عملية استخراج الكيان ، وإلحاق رسائل السجل | 1 |
| entity_summary_to_max_tokens | int | الحد الأقصى لحجم الرمز المميز لكل ملخص كيان | 500 |
| node_embedding_algorithm | str | خوارزمية لتضمين العقدة (حاليا غير مستخدم) | node2vec |
| Node2Vec_Params | dict | المعلمات لتضمين العقدة | {"dimensions": 1536,"num_walks": 10,"walk_length": 40,"window_size": 2,"iterations": 3,"random_seed": 3,} |
| incmbed_func | EmbeddingFunc | وظيفة لتوليد ناقلات التضمين من النص | openai_embedding |
| inmbeddding_batch_num | int | الحد الأقصى لحجم الدُفعة للتضمين (نصوص متعددة مرسلة لكل دفعة) | 32 |
| inmbeddding_func_max_async | int | الحد الأقصى لعدد عمليات التضمين غير المتزامنة المتزامنة | 16 |
| llm_model_func | callable | وظيفة لتوليد LLM | gpt_4o_mini_complete |
| llm_model_name | str | اسم طراز LLM للجيل | meta-llama/Llama-3.2-1B-Instruct |
| llm_model_max_token_size | int | الحد الأقصى لحجم الرمز المميز لتوليد LLM (يؤثر على ملخصات علاقة الكيان) | 32768 |
| llm_model_max_async | int | الحد الأقصى لعدد عمليات LLM غير المتزامنة المتزامنة | 16 |
| llm_model_kwargs | dict | معلمات إضافية لتوليد LLM | |
| Vector_db_storage_cls_kwargs | dict | معلمات إضافية لقاعدة بيانات المتجه (حاليا غير مستخدم) | |
| enable_llm_cache | bool | إذا كان TRUE ، فإن مخازن LLM تؤدي إلى ذاكرة التخزين المؤقت ؛ المطالبات المتكررة عودة الاستجابات المخزولة | TRUE |
| addon_params | dict | معلمات إضافية ، على سبيل المثال ، {"example_number": 1, "language": "Simplified Chinese"} : تعيين حد مثال ولغة الإخراج | example_number: all examples, language: English |
| convert_response_to_json_func | callable | لا تستخدم | convert_response_to_json |
يوفر Lightrag أيضًا تطبيقًا خادمًا قائمًا على Fastapi للوصول إلى API Restful إلى عمليات الخرقة. يتيح لك ذلك تشغيل Lightrag كخدمة والتفاعل معها من خلال طلبات HTTP.
pip install fastapi uvicorn pydantic export RAG_DIR= " your_index_directory " # Optional: Defaults to "index_default"
export OPENAI_BASE_URL= " Your OpenAI API base URL " # Optional: Defaults to "https://api.openai.com/v1"
export OPENAI_API_KEY= " Your OpenAI API key " # Required
export LLM_MODEL= " Your LLM model " # Optional: Defaults to "gpt-4o-mini"
export EMBEDDING_MODEL= " Your embedding model " # Optional: Defaults to "text-embedding-3-large"python examples/lightrag_api_openai_compatible_demo.py سيبدأ الخادم على http://0.0.0.0:8020 .
يوفر خادم API نقاط النهاية التالية:
/query{
"query" : " Your question here " ,
"mode" : " hybrid " , // Can be "naive", "local", "global", or "hybrid"
"only_need_context" : true // Optional: Defaults to false, if true, only the referenced context will be returned, otherwise the llm answer will be returned
}curl -X POST " http://127.0.0.1:8020/query "
-H " Content-Type: application/json "
-d ' {"query": "What are the main themes?", "mode": "hybrid"} ' /insert{
"text" : " Your text content here "
}curl -X POST " http://127.0.0.1:8020/insert "
-H " Content-Type: application/json "
-d ' {"text": "Content to be inserted into RAG"} ' /insert_file{
"file_path" : " path/to/your/file.txt "
}curl -X POST " http://127.0.0.1:8020/insert_file "
-H " Content-Type: application/json "
-d ' {"file_path": "./book.txt"} ' /healthcurl -X GET " http://127.0.0.1:8020/health "يمكن تكوين خادم API باستخدام متغيرات البيئة:
RAG_DIR : دليل لتخزين مؤشر RAG (افتراضي: "index_default")يتضمن واجهة برمجة التطبيقات معالجة الأخطاء الشاملة:
يمكن تنزيل مجموعة البيانات المستخدمة في Lightrag من Tommychien/Ultradomain.
يستخدم Lightrag الموجه التالي لإنشاء استعلامات عالية المستوى ، مع الكود المقابل في example/generate_query.py .
Given the following description of a dataset :
{ description }
Please identify 5 potential users who would engage with this dataset . For each user , list 5 tasks they would perform with this dataset . Then , for each ( user , task ) combination , generate 5 questions that require a high - level understanding of the entire dataset .
Output the results in the following structure :
- User 1 : [ user description ]
- Task 1 : [ task description ]
- Question 1 :
- Question 2 :
- Question 3 :
- Question 4 :
- Question 5 :
- Task 2 : [ task description ]
...
- Task 5 : [ task description ]
- User 2 : [ user description ]
...
- User 5 : [ user description ]
... لتقييم أداء نظامين RAG على استعلامات عالية المستوى ، يستخدم Lightrag الموجه التالي ، مع وجود رمز محدد متوفر في example/batch_eval.py .
- - - Role - - -
You are an expert tasked with evaluating two answers to the same question based on three criteria : ** Comprehensiveness ** , ** Diversity ** , and ** Empowerment ** .
- - - Goal - - -
You will evaluate two answers to the same question based on three criteria : ** Comprehensiveness ** , ** Diversity ** , and ** Empowerment ** .
- ** Comprehensiveness ** : How much detail does the answer provide to cover all aspects and details of the question ?
- ** Diversity ** : How varied and rich is the answer in providing different perspectives and insights on the question ?
- ** Empowerment ** : How well does the answer help the reader understand and make informed judgments about the topic ?
For each criterion , choose the better answer ( either Answer 1 or Answer 2 ) and explain why . Then , select an overall winner based on these three categories .
Here is the question :
{ query }
Here are the two answers :
** Answer 1 : **
{ answer1 }
** Answer 2 : **
{ answer2 }
Evaluate both answers using the three criteria listed above and provide detailed explanations for each criterion .
Output your evaluation in the following JSON format :
{{
"Comprehensiveness" : {{
"Winner" : "[Answer 1 or Answer 2]" ,
"Explanation" : "[Provide explanation here]"
}},
"Empowerment" : {{
"Winner" : "[Answer 1 or Answer 2]" ,
"Explanation" : "[Provide explanation here]"
}},
"Overall Winner" : {{
"Winner" : "[Answer 1 or Answer 2]" ,
"Explanation" : "[Summarize why this answer is the overall winner based on the three criteria]"
}}
}}| زراعة | CS | قانوني | مزج | |||||
|---|---|---|---|---|---|---|---|---|
| نيفراج | lightrag | نيفراج | lightrag | نيفراج | lightrag | نيفراج | lightrag | |
| الشمولية | 32.4 ٪ | 67.6 ٪ | 38.4 ٪ | 61.6 ٪ | 16.4 ٪ | 83.6 ٪ | 38.8 ٪ | 61.2 ٪ |
| تنوع | 23.6 ٪ | 76.4 ٪ | 38.0 ٪ | 62.0 ٪ | 13.6 ٪ | 86.4 ٪ | 32.4 ٪ | 67.6 ٪ |
| التمكين | 32.4 ٪ | 67.6 ٪ | 38.8 ٪ | 61.2 ٪ | 16.4 ٪ | 83.6 ٪ | 42.8 ٪ | 57.2 ٪ |
| إجمالي | 32.4 ٪ | 67.6 ٪ | 38.8 ٪ | 61.2 ٪ | 15.2 ٪ | 84.8 ٪ | 40.0 ٪ | 60.0 ٪ |
| RQ-RAG | lightrag | RQ-RAG | lightrag | RQ-RAG | lightrag | RQ-RAG | lightrag | |
| الشمولية | 31.6 ٪ | 68.4 ٪ | 38.8 ٪ | 61.2 ٪ | 15.2 ٪ | 84.8 ٪ | 39.2 ٪ | 60.8 ٪ |
| تنوع | 29.2 ٪ | 70.8 ٪ | 39.2 ٪ | 60.8 ٪ | 11.6 ٪ | 88.4 ٪ | 30.8 ٪ | 69.2 ٪ |
| التمكين | 31.6 ٪ | 68.4 ٪ | 36.4 ٪ | 63.6 ٪ | 15.2 ٪ | 84.8 ٪ | 42.4 ٪ | 57.6 ٪ |
| إجمالي | 32.4 ٪ | 67.6 ٪ | 38.0 ٪ | 62.0 ٪ | 14.4 ٪ | 85.6 ٪ | 40.0 ٪ | 60.0 ٪ |
| هايد | lightrag | هايد | lightrag | هايد | lightrag | هايد | lightrag | |
| الشمولية | 26.0 ٪ | 74.0 ٪ | 41.6 ٪ | 58.4 ٪ | 26.8 ٪ | 73.2 ٪ | 40.4 ٪ | 59.6 ٪ |
| تنوع | 24.0 ٪ | 76.0 ٪ | 38.8 ٪ | 61.2 ٪ | 20.0 ٪ | 80.0 ٪ | 32.4 ٪ | 67.6 ٪ |
| التمكين | 25.2 ٪ | 74.8 ٪ | 40.8 ٪ | 59.2 ٪ | 26.0 ٪ | 74.0 ٪ | 46.0 ٪ | 54.0 ٪ |
| إجمالي | 24.8 ٪ | 75.2 ٪ | 41.6 ٪ | 58.4 ٪ | 26.4 ٪ | 73.6 ٪ | 42.4 ٪ | 57.6 ٪ |
| Graphrag | lightrag | Graphrag | lightrag | Graphrag | lightrag | Graphrag | lightrag | |
| الشمولية | 45.6 ٪ | 54.4 ٪ | 48.4 ٪ | 51.6 ٪ | 48.4 ٪ | 51.6 ٪ | 50.4 ٪ | 49.6 ٪ |
| تنوع | 22.8 ٪ | 77.2 ٪ | 40.8 ٪ | 59.2 ٪ | 26.4 ٪ | 73.6 ٪ | 36.0 ٪ | 64.0 ٪ |
| التمكين | 41.2 ٪ | 58.8 ٪ | 45.2 ٪ | 54.8 ٪ | 43.6 ٪ | 56.4 ٪ | 50.8 ٪ | 49.2 ٪ |
| إجمالي | 45.2 ٪ | 54.8 ٪ | 48.0 ٪ | 52.0 ٪ | 47.2 ٪ | 52.8 ٪ | 50.4 ٪ | 49.6 ٪ |
يمكن العثور على جميع الكود في دليل ./reproduce .
أولاً ، نحتاج إلى استخراج سياقات فريدة في مجموعات البيانات.
def extract_unique_contexts ( input_directory , output_directory ):
os . makedirs ( output_directory , exist_ok = True )
jsonl_files = glob . glob ( os . path . join ( input_directory , '*.jsonl' ))
print ( f"Found { len ( jsonl_files ) } JSONL files." )
for file_path in jsonl_files :
filename = os . path . basename ( file_path )
name , ext = os . path . splitext ( filename )
output_filename = f" { name } _unique_contexts.json"
output_path = os . path . join ( output_directory , output_filename )
unique_contexts_dict = {}
print ( f"Processing file: { filename } " )
try :
with open ( file_path , 'r' , encoding = 'utf-8' ) as infile :
for line_number , line in enumerate ( infile , start = 1 ):
line = line . strip ()
if not line :
continue
try :
json_obj = json . loads ( line )
context = json_obj . get ( 'context' )
if context and context not in unique_contexts_dict :
unique_contexts_dict [ context ] = None
except json . JSONDecodeError as e :
print ( f"JSON decoding error in file { filename } at line { line_number } : { e } " )
except FileNotFoundError :
print ( f"File not found: { filename } " )
continue
except Exception as e :
print ( f"An error occurred while processing file { filename } : { e } " )
continue
unique_contexts_list = list ( unique_contexts_dict . keys ())
print ( f"There are { len ( unique_contexts_list ) } unique `context` entries in the file { filename } ." )
try :
with open ( output_path , 'w' , encoding = 'utf-8' ) as outfile :
json . dump ( unique_contexts_list , outfile , ensure_ascii = False , indent = 4 )
print ( f"Unique `context` entries have been saved to: { output_filename } " )
except Exception as e :
print ( f"An error occurred while saving to the file { output_filename } : { e } " )
print ( "All files have been processed." )بالنسبة للسياقات المستخرجة ، نقوم بإدخالها في نظام Lightrag.
def insert_text ( rag , file_path ):
with open ( file_path , mode = 'r' ) as f :
unique_contexts = json . load ( f )
retries = 0
max_retries = 3
while retries < max_retries :
try :
rag . insert ( unique_contexts )
break
except Exception as e :
retries += 1
print ( f"Insertion failed, retrying ( { retries } / { max_retries } ), error: { e } " )
time . sleep ( 10 )
if retries == max_retries :
print ( "Insertion failed after exceeding the maximum number of retries" )نقوم باستخراج الرموز من النصف الأول والثاني من كل سياق في مجموعة البيانات ، ثم دمجها كوصف مجموعة بيانات لإنشاء استعلامات.
tokenizer = GPT2Tokenizer . from_pretrained ( 'gpt2' )
def get_summary ( context , tot_tokens = 2000 ):
tokens = tokenizer . tokenize ( context )
half_tokens = tot_tokens // 2
start_tokens = tokens [ 1000 : 1000 + half_tokens ]
end_tokens = tokens [ - ( 1000 + half_tokens ): 1000 ]
summary_tokens = start_tokens + end_tokens
summary = tokenizer . convert_tokens_to_string ( summary_tokens )
return summaryبالنسبة للاستعلامات التي تم إنشاؤها في STEP-2 ، سنقوم باستخراجها والاستعلام عن Lightrag.
def extract_queries ( file_path ):
with open ( file_path , 'r' ) as f :
data = f . read ()
data = data . replace ( '**' , '' )
queries = re . findall ( r'- Question d+: (.+)' , data )
return queries .
├── examples
│ ├── batch_eval . py
│ ├── generate_query . py
│ ├── graph_visual_with_html . py
│ ├── graph_visual_with_neo4j . py
│ ├── lightrag_api_openai_compatible_demo . py
│ ├── lightrag_azure_openai_demo . py
│ ├── lightrag_bedrock_demo . py
│ ├── lightrag_hf_demo . py
│ ├── lightrag_lmdeploy_demo . py
│ ├── lightrag_ollama_demo . py
│ ├── lightrag_openai_compatible_demo . py
│ ├── lightrag_openai_demo . py
│ ├── lightrag_siliconcloud_demo . py
│ └── vram_management_demo . py
├── lightrag
│ ├── kg
│ │ ├── __init__ . py
│ │ └── neo4j_impl . py
│ ├── __init__ . py
│ ├── base . py
│ ├── lightrag . py
│ ├── llm . py
│ ├── operate . py
│ ├── prompt . py
│ ├── storage . py
│ └── utils . py
├── reproduce
│ ├── Step_0 . py
│ ├── Step_1_openai_compatible . py
│ ├── Step_1 . py
│ ├── Step_2 . py
│ ├── Step_3_openai_compatible . py
│ └── Step_3 . py
├── . gitignore
├── . pre - commit - config . yaml
├── Dockerfile
├── get_all_edges_nx . py
├── LICENSE
├── README . md
├── requirements . txt
├── setup . py
├── test_neo4j . py
└── test . py شكرا لجميع المساهمين لدينا!
@ article { guo2024lightrag ,
title = { LightRAG : Simple and Fast Retrieval - Augmented Generation },
author = { Zirui Guo and Lianghao Xia and Yanhua Yu and Tu Ao and Chao Huang },
year = { 2024 },
eprint = { 2410.05779 },
archivePrefix = { arXiv },
primaryClass = { cs . IR }
}شكرا لك على اهتمامك بعملنا!
