LightRAG
1.0.0
In diesem Repository wird der Code von Lightrag gehostet. Die Struktur dieses Code basiert auf Nano-Graphrag.
textract . Abbildung 1: Lightrag -Indexierungs -Flussdiagramm Abbildung 2: Abruf- und Abfragebleitungsdiagramm
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.txtVerwenden Sie den folgenden Python -Snippet (in einem Skript), um Lightrag zu initialisieren und Abfragen auszuführen:
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" )
)
),
) Wenn Sie OLLAMA-Modelle verwenden möchten, müssen Sie ein Modell ziehen, das Sie verwenden möchten, um das Modell zu verwenden und einzubetten, z. nomic-embed-text .
Dann müssen Sie nur Lightrag wie folgt einstellen:
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
)Ein funktionierendes Beispiel finden Sie test_neo4j.py.
Damit Lightrag den Arbeitskontext für den Arbeitsplatz mindestens 32.000 Token betragen sollte. Standardmäßig haben OLLAMA -Modelle eine Kontextgröße von 8K. Sie können dies auf einer von zwei Möglichkeiten erreichen:
num_ctx in Modelfile.ollama pull qwen2ollama show --modelfile qwen2 > ModelfilePARAMETER num_ctx 32768ollama create -f Modelfile qwen2mnum_ctx über Ollama API. Tiy kann llm_model_kwargs -Param verwenden, um Ollama zu konfigurieren:
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"
)
),
) Es gibt voll funktionsfähige Beispiele für examples/lightrag_ollama_demo.py das gemma2:2b -Modell verwendet, nur 4 Anforderungen parallel und festgelegt und die Kontextgröße auf 32 km festgelegt wird.
Um dieses Experiment mit niedrigem RAM -GPU auszuführen, sollten Sie ein kleines Modell und das Kontextfenster auswählen (zunehmend Kontext erhöhen den Speicherverbrauch). Wenn Sie beispielsweise dieses OLLAMA -Beispiel für die neueste Mining -GPU mit 6 GB RAM ausführen, die zur Verwendung gemma2:2b auf 26K festgelegt werden müssen. Es war in der Lage, 197 Entitäten und 19 Beziehungen zu book.txt zu finden.
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" ) Der textract unterstützt Lese -Dateitypen wie TXT, DOCX, PPTX, CSV und 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 | Typ | Erläuterung | Standard |
|---|---|---|---|
| Working_dir | str | Verzeichnis, in dem der Cache gespeichert wird | lightrag_cache+timestamp |
| KV_Storage | str | Speichertyp für Dokumente und Textbrocken. Unterstützte Typen: JsonKVStorage , OracleKVStorage | JsonKVStorage |
| vector_storage | str | Speichertyp zum Einbetten von Vektoren. Unterstützte Typen: NanoVectorDBStorage , OracleVectorDBStorage | NanoVectorDBStorage |
| Graph_Storage | str | Speichertyp für Grafikkanten und Knoten. Unterstützte Typen: NetworkXStorage , Neo4JStorage , OracleGraphStorage | NetworkXStorage |
| log_level | Protokollebene für die Laufzeit für Anwendungen | logging.DEBUG | |
| chunk_token_size | int | Maximale Tokengröße pro Chunk beim Aufteilen von Dokumenten | 1200 |
| chunk_overlap_token_size | int | Überlappungs -Token -Größe zwischen zwei Stücken beim Aufteilen von Dokumenten | 100 |
| tiktoken_model_name | str | Modellname für den Tiktoken -Encoder zur Berechnung der Token -Nummern | gpt-4o-mini |
| Entity_extract_max_gleaning | int | Anzahl der Schleifen im Entitätsextraktionsprozess und Anhang von Verlaufsnachrichten | 1 |
| Entity_Summary_to_max_tokens | int | Maximale Tokengröße für jede Entitätszusammenfassung | 500 |
| node_embedding_algorithmus | str | Algorithmus für die Knoteneinbettung (derzeit nicht verwendet) | node2vec |
| NODE2VEC_PARAMS | dict | Parameter für die Knoteneinbettung | {"dimensions": 1536,"num_walks": 10,"walk_length": 40,"window_size": 2,"iterations": 3,"random_seed": 3,} |
| Einbettung_Func | EmbeddingFunc | Funktion zum Generieren von Einbettungsvektoren aus Text | openai_embedding |
| Einbettung_Batch_num | int | Maximale Chargengröße für Einbettungsprozesse (mehrere Texte pro Stapel gesendet) | 32 |
| Einbettung_Func_Max_async | int | Maximale Anzahl gleichzeitiger asynchroner Einbettungsprozesse | 16 |
| llm_model_func | callable | Funktion für die LLM -Generation | gpt_4o_mini_complete |
| llm_model_name | str | LLM -Modellname für die Generation | meta-llama/Llama-3.2-1B-Instruct |
| llm_model_max_token_size | int | Maximale Tokengröße für die LLM -Erzeugung (beeinflusst Zusammenfassungen der Entitätsbeziehungen) | 32768 |
| llm_model_max_async | int | Maximale Anzahl gleichzeitiger asynchroner LLM -Prozesse | 16 |
| llm_model_kwargs | dict | Zusätzliche Parameter für die LLM -Generation | |
| vector_db_storage_cls_kwargs | dict | Zusätzliche Parameter für die Vektordatenbank (derzeit nicht verwendet) | |
| enable_llm_cache | bool | Wenn TRUE , speichert LLM zu Cache. Wiederholte Eingabeaufforderungen geben zwischengespeicherte Antworten zurück | TRUE |
| addon_params | dict | Zusätzliche Parameter, {"example_number": 1, "language": "Simplified Chinese"} . | example_number: all examples, language: English |
| convert_response_to_json_func | callable | Nicht benutzt | convert_response_to_json |
LightRag bietet außerdem eine Fastapi-basierte Server-Implementierung für den erholsamen API-Zugriff auf RAG-Operationen. Auf diese Weise können Sie Lightrag als Service ausführen und durch HTTP -Anfragen mit ihm interagieren.
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 Der Server startet unter http://0.0.0.0:8020 .
Der API -Server enthält die folgenden Endpunkte:
/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 "Der API -Server kann mithilfe von Umgebungsvariablen konfiguriert werden:
RAG_DIR : Verzeichnis zum Speichern des RAG -Index (Standard: "Index_Default")Die API enthält eine umfassende Fehlerbehandlung:
Der in Lightag verwendete Datensatz kann von Tommychien/Ultradomain heruntergeladen werden.
LightRag verwendet die folgende Eingabeaufforderung, um hochrangige Abfragen zu generieren, wobei der entsprechende Code in example/generate_query.py ist.
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 ]
... Um die Leistung von zwei Lappensystemen auf hochrangigen Abfragen zu bewerten, verwendet LightRag die folgende Eingabeaufforderung, wobei der spezifische Code in example/batch_eval.py verfügbar ist.
- - - 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]"
}}
}}| Landwirtschaft | CS | Legal | Mischen | |||||
|---|---|---|---|---|---|---|---|---|
| Naiverag | Lightrag | Naiverag | Lightrag | Naiverag | Lightrag | Naiverag | Lightrag | |
| Vollständigkeit | 32,4% | 67,6% | 38,4% | 61,6% | 16,4% | 83,6% | 38,8% | 61,2% |
| Diversität | 23,6% | 76,4% | 38,0% | 62,0% | 13,6% | 86,4% | 32,4% | 67,6% |
| Ermächtigung | 32,4% | 67,6% | 38,8% | 61,2% | 16,4% | 83,6% | 42,8% | 57,2% |
| Gesamt | 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 | |
| Vollständigkeit | 31,6% | 68,4% | 38,8% | 61,2% | 15,2% | 84,8% | 39,2% | 60,8% |
| Diversität | 29,2% | 70,8% | 39,2% | 60,8% | 11,6% | 88,4% | 30,8% | 69,2% |
| Ermächtigung | 31,6% | 68,4% | 36,4% | 63,6% | 15,2% | 84,8% | 42,4% | 57,6% |
| Gesamt | 32,4% | 67,6% | 38,0% | 62,0% | 14,4% | 85,6% | 40,0% | 60,0% |
| Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | Hyde | Lightrag | |
| Vollständigkeit | 26,0% | 74,0% | 41,6% | 58,4% | 26,8% | 73,2% | 40,4% | 59,6% |
| Diversität | 24,0% | 76,0% | 38,8% | 61,2% | 20,0% | 80,0% | 32,4% | 67,6% |
| Ermächtigung | 25,2% | 74,8% | 40,8% | 59,2% | 26,0% | 74,0% | 46,0% | 54,0% |
| Gesamt | 24,8% | 75,2% | 41,6% | 58,4% | 26,4% | 73,6% | 42,4% | 57,6% |
| Graphgrag | Lightrag | Graphgrag | Lightrag | Graphgrag | Lightrag | Graphgrag | Lightrag | |
| Vollständigkeit | 45,6% | 54,4% | 48,4% | 51,6% | 48,4% | 51,6% | 50,4% | 49,6% |
| Diversität | 22,8% | 77,2% | 40,8% | 59,2% | 26,4% | 73,6% | 36,0% | 64,0% |
| Ermächtigung | 41,2% | 58,8% | 45,2% | 54,8% | 43,6% | 56,4% | 50,8% | 49,2% |
| Gesamt | 45,2% | 54,8% | 48,0% | 52,0% | 47,2% | 52,8% | 50,4% | 49,6% |
Der gesamte Code befindet sich im Verzeichnis ./reproduce .
Zunächst müssen wir einzigartige Kontexte in den Datensätzen extrahieren.
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." )Für die extrahierten Kontexte setzen wir sie in das Lightrag -System ein.
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" )Wir extrahieren Token aus der ersten und zweiten Hälfte jedes Kontextes im Datensatz und kombinieren sie dann als Datensatzbeschreibungen, um Abfragen zu generieren.
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 summaryFür die in Schritt-2 generierten Abfragen werden wir sie extrahieren und Lightrag abfragen.
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 Vielen Dank an alle unsere Mitwirkenden!
@ 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 }
}Vielen Dank für Ihr Interesse an unserer Arbeit!
