railseek6/stdout.txt

=======================================
Starting LightRAG Production System
=======================================
Checking for existing server on port 3015...
No existing server found on port 3015.
Starting LightRAG server...
Starting LightRAG server with fixed encoding...
Command: C:\Program Files\Python311\python.exe -m lightrag.api.lightrag_server --port 3015 --host 0.0.0.0 --working-dir rag_storage --input-dir ../inputs --key jleu1212 --auto-scan-at-startup --llm-binding openai --embedding-binding ollama --rerank-binding jina
Starting server on http://0.0.0.0:3015

Server output:
--------------------------------------------------
WARNING:root:>> Forcing workers=1 in uvicorn mode(Ignoring workers=2)
DEBUG: Authentication disabled - using guest access only
DEBUG: Final accounts (disabled): {}

LightRAG log file: C:\aaWORK\railseek6\LightRAG-main\logs\lightrag.log


    ????????????????????????????????????????????????????????????????
    ?                LightRAG Server v1.4.8.1/0222                 ?
    ?         Fast, Lightweight RAG Server Implementation          ?
    ????????????????????????????????????????????????????????????????
    

? Server Configuration:
    ?? Host: 0.0.0.0
    ?? Port: 3015
    ?? Workers: 1
    ?? Timeout: 300
    ?? CORS Origins: *
    ?? SSL Enabled: False
    ?? Ollama Emulating Model: lightrag:latest
    ?? Log Level: INFO
    ?? Verbose Debug: False
    ?? History Turns: 0
    ?? API Key: Set
    ?? JWT Auth: Disabled

? Directory Configuration:
    ?? Working Directory: C:\aaWORK\railseek6\LightRAG-main\rag_storage
    ?? Input Directory: C:\aaWORK\railseek6\inputs

? LLM Configuration:
    ?? Binding: openai
    ?? Host: https://api.openai.com/v1
    ?? Model: deepseek-chat
    ?? Max Async for LLM: 4
    ?? Summary Context Size: 12000
    ?? LLM Cache Enabled: True
    ?? LLM Cache for Extraction Enabled: True

? Embedding Configuration:
    ?? Binding: ollama
    ?? Host: http://localhost:11434
    ?? Model: bge-m3:latest
    ?? Dimensions: 1024

?? RAG Configuration:
    ?? Summary Language: English
    ?? Entity Types: ['Person', 'Organization', 'Location', 'Event', 'Concept', 'Method', 'Content', 'Data', 'Artifact', 'NaturalObject']
    ?? Max Parallel Insert: 2
    ?? Chunk Size: 1200
    ?? Chunk Overlap Size: 100
    ?? Cosine Threshold: 0.2
    ?? Top-K: 40
    ?? Force LLM Summary on Merge: 8

? Storage Configuration:
    ?? KV Storage: JsonKVStorage
    ?? Vector Storage: NanoVectorDBStorage
    ?? Graph Storage: NetworkXStorage
    ?? Document Status Storage: JsonDocStatusStorage
    ?? Workspace: -

? Server starting up...


? Server Access Information:
    ?? WebUI (local): http://localhost:3015
    ?? Remote Access: http://<your-ip-address>:3015
    ?? API Documentation (local): http://localhost:3015/docs
    ?? Alternative Documentation (local): http://localhost:3015/redoc

? Note:
    Since the server is running on 0.0.0.0:
    - Use 'localhost' or '127.0.0.1' for local access
    - Use your machine's IP address for remote access
    - To find your IP address:
      ? Windows: Run 'ipconfig' in terminal
      ? Linux/Mac: Run 'ifconfig' or 'ip addr' in terminal
    

??  Security Notice:
    API Key authentication is enabled.
    Make sure to include the X-API-Key header in all your requests.
    
INFO: OpenAI LLM Options: {}
INFO: Ollama Embedding Options: {}
INFO: Reranking is enabled: jina-reranker-v2-base-multilingual using jina provider
INFO: [_] Loaded graph from C:\aaWORK\railseek6\LightRAG-main\rag_storage\graph_chunk_entity_relation.graphml with 616 nodes, 0 edges
INFO: Started server process [30776]
INFO: Waiting for application startup.
INFO: [_] Process 30776 KV load full_docs with 2 records
INFO: [_] Process 30776 KV load text_chunks with 24 records
INFO: [_] Process 30776 KV load full_entities with 2 records
INFO: [_] Process 30776 KV load full_relations with 0 records
INFO: [_] Process 30776 KV load llm_response_cache with 0 records
INFO: [_] Process 30776 doc status load doc_status with 2 records
INFO: Process 30776 auto scan task started at startup.
INFO: Found 0 files to index.
INFO: No upload file found, check if there are any documents in the queue...
INFO: Application startup complete.
INFO: No documents to process
INFO: Uvicorn running on http://0.0.0.0:3015 (Press CTRL+C to quit)