LightRAG
1.0.0
Este repositório hospeda o código do Lightrag. A estrutura deste código é baseada em nano-grafrag.
textract . Figura 1: Fluxograma de indexação do Lightrag Figura 2: Recuperação do Lightrag e Fluxograma de Consulta
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.txtUse o trecho Python abaixo (em um script) para inicializar o Lightrag e executar consultas:
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" )
)
),
) Se você deseja usar os modelos Ollama, precisará puxar o modelo que planeja usar e incorporar o modelo, por exemplo nomic-embed-text .
Então você só precisa definir o Lightrag da seguinte maneira:
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
)Consulte test_neo4j.py para um exemplo de trabalho.
Para que o contexto do Lightrag para funcionar deve ser de pelo menos 32 mil tokens. Por padrão, os modelos Ollama têm tamanho de contexto de 8k. Você pode conseguir isso usando uma das duas maneiras:
num_ctx no modelfile.ollama pull qwen2ollama show --modelfile qwen2 > ModelfilePARAMETER num_ctx 32768ollama create -f Modelfile qwen2mnum_ctx via API Ollama. Tiy pode usar llm_model_kwargs param para configurar o 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"
)
),
) Existem examples/lightrag_ollama_demo.py que utilizam o modelo gemma2:2b , executa apenas 4 solicitações em paralelo e define o tamanho do contexto como 32k.
Para executar esse experimento na GPU de baixo RAM, você deve selecionar o modelo pequeno e ajustar a janela de contexto (aumentando o aumento do consumo de memória). Por exemplo, executando este exemplo de Ollama na GPU de mineração reaproveitada com 6 GB de RAM necessária para definir o tamanho do contexto para 26k enquanto estiver usando gemma2:2b . Foi capaz de encontrar 197 entidades e 19 relações no 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" ) O textract suporta tipos de arquivos de leitura, como TXT, DOCX, PPTX, CSV e 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 ()| Parâmetro | Tipo | Explicação | Padrão |
|---|---|---|---|
| Trabalhando_dir | str | Diretório onde o cache será armazenado | lightrag_cache+timestamp |
| kv_storage | str | Tipo de armazenamento para documentos e pedaços de texto. Tipos suportados: JsonKVStorage , OracleKVStorage | JsonKVStorage |
| Vector_storage | str | Tipo de armazenamento para incorporar vetores. Tipos suportados: NanoVectorDBStorage , OracleVectorDBStorage | NanoVectorDBStorage |
| Graph_storage | str | Tipo de armazenamento para bordas e nós do gráfico. Tipos suportados: NetworkXStorage , Neo4JStorage , OracleGraphStorage | NetworkXStorage |
| log_level | Nível de log para o tempo de execução do aplicativo | logging.DEBUG | |
| chunk_token_size | int | Tamanho máximo do token por pedaço ao dividir documentos | 1200 |
| chunk_overlap_token_size | int | Sobreposição de tamanho de token entre dois pedaços ao dividir documentos | 100 |
| tiktoken_model_name | str | Nome do modelo para o codificador Tiktoken usado para calcular números de token | gpt-4o-mini |
| entity_extract_max_gleaning | int | Número de loops no processo de extração de entidades, anexando mensagens de histórico | 1 |
| entity_summary_to_max_tokens | int | Tamanho máximo do token para cada resumo da entidade | 500 |
| node_embedding_algorithm | str | Algoritmo para incorporação de nó (atualmente não usado) | node2vec |
| node2vec_params | dict | Parâmetros para incorporação de nó | {"dimensions": 1536,"num_walks": 10,"walk_length": 40,"window_size": 2,"iterations": 3,"random_seed": 3,} |
| incorpingding_func | EmbeddingFunc | Função para gerar vetores de incorporação do texto | openai_embedding |
| incorpingding_batch_num | int | Tamanho máximo do lote para os processos de incorporação (vários textos enviados por lote) | 32 |
| incorpingding_func_max_async | int | Número máximo de processos simultâneos de incorporação assíncrona | 16 |
| llm_model_func | callable | Função para geração LLM | gpt_4o_mini_complete |
| llm_model_name | str | Nome do modelo LLM para geração | meta-llama/Llama-3.2-1B-Instruct |
| llm_model_max_token_size | int | Tamanho máximo do token para geração LLM (afeta os resumos da relação da entidade) | 32768 |
| llm_model_max_async | int | Número máximo de processos LLM assíncronos simultâneos | 16 |
| llm_model_kwargs | dict | Parâmetros adicionais para geração LLM | |
| vetor_db_storage_cls_kwargs | dict | Parâmetros adicionais para o banco de dados vetorial (atualmente não usado) | |
| enable_llm_cache | bool | Se TRUE , as lojas LLM resultam em cache; Pumculos repetidos retornam respostas em cache | TRUE |
| addon_params | dict | Parâmetros adicionais, por exemplo, {"example_number": 1, "language": "Simplified Chinese"} : define o limite de exemplo e a linguagem de saída | example_number: all examples, language: English |
| Convert_Response_to_json_func | callable | Não usado | convert_response_to_json |
O Lightrag também fornece uma implementação de servidor baseada em FASTAPI para acesso API RESTful às operações de RAG. Isso permite que você execute o Lightrag como um serviço e interaja com ele por meio de solicitações 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 O servidor começará em http://0.0.0.0:8020 .
O servidor API fornece os seguintes pontos de extremidade:
/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 "O servidor API pode ser configurado usando variáveis de ambiente:
RAG_DIR : diretório para armazenar o índice de pano (padrão: "index_default")A API inclui manuseio abrangente de erros:
O conjunto de dados usado no Lightrag pode ser baixado de Tommychien/Ultradomain.
O Lightrag usa o seguinte prompt para gerar consultas de alto nível, com o código correspondente no 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 ]
... Para avaliar o desempenho de dois sistemas de pano em consultas de alto nível, o Lightrag usa o seguinte prompt, com o código específico disponível no 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]"
}}
}}| Agricultura | Cs | Jurídico | Mistura | |||||
|---|---|---|---|---|---|---|---|---|
| Ingentag | Lightrag | Ingentag | Lightrag | Ingentag | Lightrag | Ingentag | Lightrag | |
| Abrangência | 32,4% | 67,6% | 38,4% | 61,6% | 16,4% | 83,6% | 38,8% | 61,2% |
| Diversidade | 23,6% | 76,4% | 38,0% | 62,0% | 13,6% | 86,4% | 32,4% | 67,6% |
| Empoderamento | 32,4% | 67,6% | 38,8% | 61,2% | 16,4% | 83,6% | 42,8% | 57,2% |
| Geral | 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 | |
| Abrangência | 31,6% | 68,4% | 38,8% | 61,2% | 15,2% | 84,8% | 39,2% | 60,8% |
| Diversidade | 29,2% | 70,8% | 39,2% | 60,8% | 11,6% | 88,4% | 30,8% | 69,2% |
| Empoderamento | 31,6% | 68,4% | 36,4% | 63,6% | 15,2% | 84,8% | 42,4% | 57,6% |
| Geral | 32,4% | 67,6% | 38,0% | 62,0% | 14,4% | 85,6% | 40,0% | 60,0% |
| Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | |
| Abrangência | 26,0% | 74,0% | 41,6% | 58,4% | 26,8% | 73,2% | 40,4% | 59,6% |
| Diversidade | 24,0% | 76,0% | 38,8% | 61,2% | 20,0% | 80,0% | 32,4% | 67,6% |
| Empoderamento | 25,2% | 74,8% | 40,8% | 59,2% | 26,0% | 74,0% | 46,0% | 54,0% |
| Geral | 24,8% | 75,2% | 41,6% | 58,4% | 26,4% | 73,6% | 42,4% | 57,6% |
| Graphrag | Lightrag | Graphrag | Lightrag | Graphrag | Lightrag | Graphrag | Lightrag | |
| Abrangência | 45,6% | 54,4% | 48,4% | 51,6% | 48,4% | 51,6% | 50,4% | 49,6% |
| Diversidade | 22,8% | 77,2% | 40,8% | 59,2% | 26,4% | 73,6% | 36,0% | 64,0% |
| Empoderamento | 41,2% | 58,8% | 45,2% | 54,8% | 43,6% | 56,4% | 50,8% | 49,2% |
| Geral | 45,2% | 54,8% | 48,0% | 52,0% | 47,2% | 52,8% | 50,4% | 49,6% |
Todo o código pode ser encontrado no diretório ./reproduce .
Primeiro, precisamos extrair contextos exclusivos nos conjuntos de dados.
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." )Para os contextos extraídos, os inserimos no sistema 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" )Extraímos tokens do primeiro e da segunda metade de cada contexto no conjunto de dados e os combinamos como descrições do conjunto de dados para gerar consultas.
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 summaryPara as consultas geradas na etapa-2, as extraímos e consultaremos o 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 Obrigado a todos os nossos colaboradores!
@ 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 }
}Obrigado pelo seu interesse em nosso trabalho!
