LightRAG
1.0.0
Repositori ini meng -host kode Lightrag. Struktur kode ini didasarkan pada nano-graphrag.
textract . Gambar 1: Lightrag Indexing Flowchart Gambar 2: Lightrag Retrieval dan Querying Flowchart
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.txtGunakan cuplikan Python di bawah ini (dalam skrip) untuk menginisialisasi lightrag dan melakukan pertanyaan:
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" )
)
),
) Jika Anda ingin menggunakan model Ollama, Anda perlu menarik model yang Anda rencanakan untuk digunakan dan menanamkan model, misalnya nomic-embed-text .
Maka Anda hanya perlu mengatur lightrag sebagai berikut:
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
)Lihat test_neo4j.py untuk contoh yang berfungsi.
Agar konteks Lightrag bekerja harus setidaknya 32K token. Secara default model Ollama memiliki ukuran konteks 8K. Anda dapat mencapai ini menggunakan salah satu dari dua cara:
num_ctx di Modelfile.ollama pull qwen2ollama show --modelfile qwen2 > ModelfilePARAMETER num_ctx 32768ollama create -f Modelfile qwen2mnum_ctx via Ollama API. Tiy dapat menggunakan param llm_model_kwargs untuk mengonfigurasi 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"
)
),
) Ada examples/lightrag_ollama_demo.py yang menggunakan model gemma2:2b , hanya menjalankan 4 permintaan secara paralel dan mengatur ukuran konteks ke 32K.
Untuk menjalankan percobaan ini pada GPU RAM rendah, Anda harus memilih jendela kecil model dan tune (meningkatkan konteks meningkatkan konsumsi memori). Misalnya, menjalankan contoh ollama ini pada GPU penambangan yang digunakan kembali dengan RAM 6GB yang diperlukan untuk menetapkan ukuran konteks ke 26k saat menggunakan gemma2:2b . Itu mampu menemukan 197 entitas dan 19 hubungan di 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" ) textract mendukung jenis file membaca seperti TXT, DOCX, PPTX, CSV, dan 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 ()| Parameter | Jenis | Penjelasan | Bawaan |
|---|---|---|---|
| working_dir | str | Direktori di mana cache akan disimpan | lightrag_cache+timestamp |
| kv_storage | str | Jenis penyimpanan untuk dokumen dan potongan teks. Jenis yang Didukung: JsonKVStorage , OracleKVStorage | JsonKVStorage |
| vector_storage | str | Jenis Penyimpanan untuk Vektor Menyematkan. Jenis yang Didukung: NanoVectorDBStorage , OracleVectorDBStorage | NanoVectorDBStorage |
| Graph_Storage | str | Jenis penyimpanan untuk tepi grafik dan node. Jenis yang Didukung: NetworkXStorage , Neo4JStorage , OracleGraphStorage | NetworkXStorage |
| log_level | Level log untuk runtime aplikasi | logging.DEBUG | |
| chunk_token_size | int | Ukuran token maksimum per potongan saat membagi dokumen | 1200 |
| chunk_overlap_token_size | int | Ukuran token yang tumpang tindih antara dua potongan saat membagi dokumen | 100 |
| Tiktoken_model_name | str | Nama model untuk encoder TikToken yang digunakan untuk menghitung nomor token | gpt-4o-mini |
| entity_extract_max_gleaning | int | Jumlah loop dalam proses ekstraksi entitas, menambahkan pesan sejarah | 1 |
| entity_summary_to_max_tokens | int | Ukuran token maksimum untuk setiap ringkasan entitas | 500 |
| node_embedding_algorithm | str | Algoritma untuk embedding simpul (saat ini tidak digunakan) | node2vec |
| node2vec_params | dict | Parameter untuk penyematan simpul | {"dimensions": 1536,"num_walks": 10,"walk_length": 40,"window_size": 2,"iterations": 3,"random_seed": 3,} |
| embedding_func | EmbeddingFunc | Fungsi untuk menghasilkan vektor embedding dari teks | openai_embedding |
| embedding_batch_num | int | Ukuran batch maksimum untuk proses penyematan (beberapa teks yang dikirim per batch) | 32 |
| embedding_func_max_async | int | Jumlah maksimum proses embedding asinkron bersamaan | 16 |
| llm_model_func | callable | Fungsi untuk generasi LLM | gpt_4o_mini_complete |
| llm_model_name | str | Nama model LLM untuk generasi | meta-llama/Llama-3.2-1B-Instruct |
| llm_model_max_token_size | int | Ukuran token maksimum untuk generasi LLM (mempengaruhi ringkasan hubungan entitas) | 32768 |
| llm_model_max_async | int | Jumlah maksimum proses LLM asinkron bersamaan | 16 |
| llm_model_kwargs | dict | Parameter tambahan untuk generasi LLM | |
| vector_db_storage_cls_kwargs | dict | Parameter tambahan untuk database vektor (saat ini tidak digunakan) | |
| enable_llm_cache | bool | Jika TRUE , Stores LLM menghasilkan cache; Prompt berulang respons yang di -cache | TRUE |
| addon_params | dict | Parameter tambahan, misalnya, {"example_number": 1, "language": "Simplified Chinese"} : Mengatur batas contoh dan bahasa output | example_number: all examples, language: English |
| convert_response_to_json_func | callable | Tidak digunakan | convert_response_to_json |
Lightrag juga menyediakan implementasi server berbasis FASTAPI untuk akses API yang RESTful ke operasi RAG. Ini memungkinkan Anda untuk menjalankan Lightrag sebagai layanan dan berinteraksi dengannya melalui permintaan 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 Server akan mulai di http://0.0.0.0:8020 .
Server API menyediakan titik akhir berikut:
/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 "Server API dapat dikonfigurasi menggunakan variabel lingkungan:
RAG_DIR : Direktori untuk menyimpan indeks kain (default: "index_default")API termasuk penanganan kesalahan komprehensif:
Dataset yang digunakan di Lightrag dapat diunduh dari Tommychien/Ultradomain.
Lightrag menggunakan prompt berikut untuk menghasilkan kueri tingkat tinggi, dengan kode yang sesuai dalam 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 ]
... Untuk mengevaluasi kinerja dua sistem kain pada kueri tingkat tinggi, Lightrag menggunakan prompt berikut, dengan kode spesifik yang tersedia dalam 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]"
}}
}}| Pertanian | CS | Legal | Mencampur | |||||
|---|---|---|---|---|---|---|---|---|
| Naiverag | Lightrag | Naiverag | Lightrag | Naiverag | Lightrag | Naiverag | Lightrag | |
| Kelengkapan | 32,4% | 67,6% | 38,4% | 61,6% | 16,4% | 83,6% | 38,8% | 61,2% |
| Keberagaman | 23,6% | 76,4% | 38,0% | 62,0% | 13,6% | 86,4% | 32,4% | 67,6% |
| Pemberdayaan | 32,4% | 67,6% | 38,8% | 61,2% | 16,4% | 83,6% | 42,8% | 57,2% |
| Keseluruhan | 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 | |
| Kelengkapan | 31,6% | 68,4% | 38,8% | 61,2% | 15,2% | 84,8% | 39,2% | 60,8% |
| Keberagaman | 29,2% | 70,8% | 39,2% | 60,8% | 11,6% | 88,4% | 30,8% | 69,2% |
| Pemberdayaan | 31,6% | 68,4% | 36,4% | 63,6% | 15,2% | 84,8% | 42,4% | 57,6% |
| Keseluruhan | 32,4% | 67,6% | 38,0% | 62,0% | 14,4% | 85,6% | 40,0% | 60,0% |
| Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | |
| Kelengkapan | 26,0% | 74,0% | 41,6% | 58,4% | 26,8% | 73,2% | 40,4% | 59,6% |
| Keberagaman | 24,0% | 76,0% | 38,8% | 61,2% | 20,0% | 80,0% | 32,4% | 67,6% |
| Pemberdayaan | 25,2% | 74,8% | 40,8% | 59,2% | 26,0% | 74,0% | 46,0% | 54,0% |
| Keseluruhan | 24,8% | 75,2% | 41,6% | 58,4% | 26,4% | 73,6% | 42,4% | 57,6% |
| Graphrag | Lightrag | Graphrag | Lightrag | Graphrag | Lightrag | Graphrag | Lightrag | |
| Kelengkapan | 45,6% | 54,4% | 48,4% | 51,6% | 48,4% | 51,6% | 50,4% | 49,6% |
| Keberagaman | 22,8% | 77,2% | 40,8% | 59,2% | 26,4% | 73,6% | 36,0% | 64,0% |
| Pemberdayaan | 41,2% | 58,8% | 45,2% | 54,8% | 43,6% | 56,4% | 50,8% | 49,2% |
| Keseluruhan | 45,2% | 54,8% | 48,0% | 52,0% | 47,2% | 52,8% | 50,4% | 49,6% |
Semua kode dapat ditemukan di direktori ./reproduce .
Pertama, kita perlu mengekstrak konteks unik dalam dataset.
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." )Untuk konteks yang diekstraksi, kami memasukkannya ke dalam sistem 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" )Kami mengekstrak token dari paruh pertama dan kedua dari setiap konteks dalam dataset, kemudian menggabungkannya sebagai deskripsi dataset untuk menghasilkan kueri.
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 summaryUntuk kueri yang dihasilkan dalam Langkah-2, kami akan mengekstraknya dan meminta 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 Terima kasih untuk semua kontributor kami!
@ 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 }
}Terima kasih atas minat Anda pada pekerjaan kami!
