LightRAG

async def llm_model_func(
    prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **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_embed(
        texts,
        model="solar-embedding-1-large-query",
        api_key=os.getenv("UPSTAGE_API_KEY"),
        base_url="https://api.upstage.ai/v1/solar"
    )

async def initialize_rag():
    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
        )
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag

# 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_embed(
            texts,
            tokenizer=AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2"),
            embed_model=AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
        )
    ),
)

# 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_embed(
            texts,
            embed_model="nomic-embed-text"
        )
    ),
)

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"
        )
    ),
)

# Using LlamaIndex with direct OpenAI access
import asyncio
from lightrag import LightRAG
from lightrag.llm.llama_index_impl import llama_index_complete_if_cache, llama_index_embed
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
from lightrag.kg.shared_storage import initialize_pipeline_status
from lightrag.utils import setup_logger

# Setup log handler for LightRAG
setup_logger("lightrag", level="INFO")

async def initialize_rag():
    rag = LightRAG(
        working_dir="your/path",
        llm_model_func=llama_index_complete_if_cache,  # LlamaIndex-compatible completion function
        embedding_func=EmbeddingFunc(    # LlamaIndex-compatible embedding function
            embedding_dim=1536,
            max_token_size=8192,
            func=lambda texts: llama_index_embed(texts, embed_model=embed_model)
        ),
    )

    await rag.initialize_storages()
    await initialize_pipeline_status()

    return rag

def main():
    # Initialize RAG instance
    rag = asyncio.run(initialize_rag())

    with open("./book.txt", "r", encoding="utf-8") 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"))
    )

if __name__ == "__main__":
    main()

# Create conversation history
conversation_history = [
    {"role": "user", "content": "What is the main character's attitude towards Christmas?"},
    {"role": "assistant", "content": "At the beginning of the story, Ebenezer Scrooge has a very negative attitude towards Christmas..."},
    {"role": "user", "content": "How does his attitude change?"}
]

# Create query parameters with conversation history
query_param = QueryParam(
    mode="mix",  # or any other mode: "local", "global", "hybrid"
    conversation_history=conversation_history,  # Add the conversation history
    history_turns=3  # Number of recent conversation turns to consider
)

# Make a query that takes into account the conversation history
response = rag.query(
    "What causes this change in his character?",
    param=query_param
)

# Create query parameters
query_param = QueryParam(
    mode="hybrid",  # or other mode: "local", "global", "hybrid", "mix" and "naive"
)

# Example 1: Using the default system prompt
response_default = rag.query(
    "What are the primary benefits of renewable energy?",
    param=query_param
)
print(response_default)

# Example 2: Using a custom prompt
custom_prompt = """
You are an expert assistant in environmental science. Provide detailed and structured answers with examples.
---Conversation History---
{history}

---Knowledge Base---
{context_data}

---Response Rules---

- Target format and length: {response_type}
"""
response_custom = rag.query(
    "What are the primary benefits of renewable energy?",
    param=query_param,
    system_prompt=custom_prompt  # Pass the custom prompt
)
print(response_custom)

rag.query_with_separate_keyword_extraction(
    query="Explain the law of gravity",
    prompt="Provide a detailed explanation suitable for high school students studying physics.",
    param=QueryParam(mode="hybrid")
)

# Basic Insert
rag.insert("Text")

# Basic Batch Insert: Insert multiple texts at once
rag.insert(["TEXT1", "TEXT2",...])

# Batch Insert with custom batch size configuration
rag = LightRAG(
    working_dir=WORKING_DIR,
    addon_params={
        "insert_batch_size": 4  # Process 4 documents per batch
    }
)

rag.insert(["TEXT1", "TEXT2", "TEXT3", ...])  # Documents will be processed in batches of 4

# Insert single text, and provide ID for it
rag.insert("TEXT1", ids=["ID_FOR_TEXT1"])

# Insert multiple texts, and provide IDs for them
rag.insert(["TEXT1", "TEXT2",...], ids=["ID_FOR_TEXT1", "ID_FOR_TEXT2"])

rag = LightRAG(..)

await rag.apipeline_enqueue_documents(input)
# Your routine in loop
await rag.apipeline_process_enqueue_documents(input)

import textract

file_path = 'TEXT.pdf'
text_content = textract.process(file_path)

rag.insert(text_content.decode('utf-8'))

custom_kg = {
    "chunks": [
        {
            "content": "Alice and Bob are collaborating on quantum computing research.",
            "source_id": "doc-1"
        }
    ],
    "entities": [
        {
            "entity_name": "Alice",
            "entity_type": "person",
            "description": "Alice is a researcher specializing in quantum physics.",
            "source_id": "doc-1"
        },
        {
            "entity_name": "Bob",
            "entity_type": "person",
            "description": "Bob is a mathematician.",
            "source_id": "doc-1"
        },
        {
            "entity_name": "Quantum Computing",
            "entity_type": "technology",
            "description": "Quantum computing utilizes quantum mechanical phenomena for computation.",
            "source_id": "doc-1"
        }
    ],
    "relationships": [
        {
            "src_id": "Alice",
            "tgt_id": "Bob",
            "description": "Alice and Bob are research partners.",
            "keywords": "collaboration research",
            "weight": 1.0,
            "source_id": "doc-1"
        },
        {
            "src_id": "Alice",
            "tgt_id": "Quantum Computing",
            "description": "Alice conducts research on quantum computing.",
            "keywords": "research expertise",
            "weight": 1.0,
            "source_id": "doc-1"
        },
        {
            "src_id": "Bob",
            "tgt_id": "Quantum Computing",
            "description": "Bob researches quantum computing.",
            "keywords": "research application",
            "weight": 1.0,
            "source_id": "doc-1"
        }
    ]
}

rag.insert_custom_kg(custom_kg)

# Define documents and their file paths
documents = ["Document content 1", "Document content 2"]
file_paths = ["path/to/doc1.txt", "path/to/doc2.txt"]

# Insert documents with file paths
rag.insert(documents, file_paths=file_paths)

export NEO4J_URI="neo4j://localhost:7687"
export NEO4J_USERNAME="neo4j"
export NEO4J_PASSWORD="password"

# Setup logger for LightRAG
setup_logger("lightrag", level="INFO")

# When you launch the project be sure to override the default KG: NetworkX
# by specifying kg="Neo4JStorage".

# Note: Default settings use NetworkX
# Initialize LightRAG with Neo4J implementation.
async def initialize_rag():
    rag = LightRAG(
        working_dir=WORKING_DIR,
        llm_model_func=gpt_4o_mini_complete,  # Use gpt_4o_mini_complete LLM model
        graph_storage="Neo4JStorage", #<-----------override KG default
    )

    # Initialize database connections
    await rag.initialize_storages()
    # Initialize pipeline status for document processing
    await initialize_pipeline_status()

    return rag

async def embedding_func(texts: list[str]) -> np.ndarray:
    model = SentenceTransformer('all-MiniLM-L6-v2')
    embeddings = model.encode(texts, convert_to_numpy=True)
    return embeddings

# Initialize LightRAG with the LLM model function and embedding function
rag = LightRAG(
    working_dir=WORKING_DIR,
    llm_model_func=llm_model_func,
    embedding_func=EmbeddingFunc(
        embedding_dim=384,
        max_token_size=8192,
        func=embedding_func,
    ),
    vector_storage="FaissVectorDBStorage",
    vector_db_storage_cls_kwargs={
        "cosine_better_than_threshold": 0.3  # Your desired threshold
    }
)

# Create new entity
entity = rag.create_entity("Google", {
    "description": "Google is a multinational technology company specializing in internet-related services and products.",
    "entity_type": "company"
})

# Create another entity
product = rag.create_entity("Gmail", {
    "description": "Gmail is an email service developed by Google.",
    "entity_type": "product"
})

# Create relation between entities
relation = rag.create_relation("Google", "Gmail", {
    "description": "Google develops and operates Gmail.",
    "keywords": "develops operates service",
    "weight": 2.0
})

# Edit an existing entity
updated_entity = rag.edit_entity("Google", {
    "description": "Google is a subsidiary of Alphabet Inc., founded in 1998.",
    "entity_type": "tech_company"
})

# Rename an entity (with all its relationships properly migrated)
renamed_entity = rag.edit_entity("Gmail", {
    "entity_name": "Google Mail",
    "description": "Google Mail (formerly Gmail) is an email service."
})

# Edit a relation between entities
updated_relation = rag.edit_relation("Google", "Google Mail", {
    "description": "Google created and maintains Google Mail service.",
    "keywords": "creates maintains email service",
    "weight": 3.0
})

# Basic CSV export (default format)
rag.export_data("knowledge_graph.csv")

# Specify any format
rag.export_data("output.xlsx", file_format="excel")

#Export data in CSV format
rag.export_data("graph_data.csv", file_format="csv")

# Export data in Excel sheet
rag.export_data("graph_data.xlsx", file_format="excel")

# Export data in markdown format
rag.export_data("graph_data.md", file_format="md")

# Export data in Text
rag.export_data("graph_data.txt", file_format="txt")

rag.export_data("complete_data.csv", include_vector_data=True)

# Basic entity merging
rag.merge_entities(
    source_entities=["Artificial Intelligence", "AI", "Machine Intelligence"],
    target_entity="AI Technology"
)

# Define custom merge strategy for different fields
rag.merge_entities(
    source_entities=["John Smith", "Dr. Smith", "J. Smith"],
    target_entity="John Smith",
    merge_strategy={
        "description": "concatenate",  # Combine all descriptions
        "entity_type": "keep_first",   # Keep the entity type from the first entity
        "source_id": "join_unique"     # Combine all unique source IDs
    }
)

# Specify exact values for the merged entity
rag.merge_entities(
    source_entities=["New York", "NYC", "Big Apple"],
    target_entity="New York City",
    target_entity_data={
        "entity_type": "LOCATION",
        "description": "New York City is the most populous city in the United States.",
    }
)

# Merge company entities with both strategy and custom data
rag.merge_entities(
    source_entities=["Microsoft Corp", "Microsoft Corporation", "MSFT"],
    target_entity="Microsoft",
    merge_strategy={
        "description": "concatenate",  # Combine all descriptions
        "source_id": "join_unique"     # Combine source IDs
    },
    target_entity_data={
        "entity_type": "ORGANIZATION",
    }
)

# Clear all cache
await rag.aclear_cache()

# Clear local mode cache
await rag.aclear_cache(modes=["local"])

# Clear extraction cache
await rag.aclear_cache(modes=["default"])

# Clear multiple modes
await rag.aclear_cache(modes=["local", "global", "hybrid"])

# Synchronous version
rag.clear_cache(modes=["local"])

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]
    ...

---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]"
    }}
}}

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.")

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")

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 summary

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