- tools/scripts/llm-key-hunter: GitHub leak hunting pipeline (hunt_*, pivot miner, two-layer verify/content caches, per-provider verification) - usable_keys: verified key vault across 12 providers (deepseek, minimax, volcanoark, longcat, codingplan, zhipu free-tier, mimo, siliconflow, etc.) - .grok/skills/llm-key-hunter: operator skill for the hunt/verify/vault flow - NewAPI channel import scripts and CDP capture helpers - Result verdict buckets (excluding multi-GB blob caches and dedup dumps)
73 lines
1.7 KiB
Plaintext
73 lines
1.7 KiB
Plaintext
# =====================
|
|
# GLM / LLM
|
|
# =====================
|
|
GLM_API_KEY=916c5afa2ce9443380593a244c711b86.7ca8xGUh9u1MB3Mu
|
|
GLM_MODEL_NAME=glm-5
|
|
GLM_API_BASE=https://open.bigmodel.cn/api/paas/v4
|
|
GLM_TEMPERATURE=0.4
|
|
GLM_MAX_TOKENS=64000
|
|
|
|
# =====================
|
|
# Milvus
|
|
# =====================
|
|
MILVUS_HOST=localhost
|
|
MILVUS_PORT=19530
|
|
MILVUS_COLLECTION_NAME=rag_knowledge_base
|
|
MILVUS_USER=
|
|
MILVUS_PASSWORD=
|
|
|
|
# =====================
|
|
# Embedding / Reranker
|
|
# =====================
|
|
EMBEDDING_MODEL_NAME=./models/bge-small-zh-v1.5
|
|
EMBEDDING_DEVICE=mps
|
|
EMBEDDING_DIMENSION=512
|
|
RERANKER_MODEL_NAME=./models/bge-reranker-base
|
|
RERANKER_TOP_K=5
|
|
|
|
# =====================
|
|
# Book-aware Splitting
|
|
# =====================
|
|
CHUNK_SIZE=500
|
|
CHUNK_OVERLAP=100
|
|
BOOK_MD_EPUB_CHUNK_SIZE=1000
|
|
BOOK_MD_EPUB_CHUNK_OVERLAP=150
|
|
BOOK_PDF_CHUNK_SIZE=1000
|
|
BOOK_PDF_CHUNK_OVERLAP=100
|
|
BOOK_TXT_CHUNK_SIZE=500
|
|
BOOK_TXT_CHUNK_OVERLAP=100
|
|
|
|
# =====================
|
|
# Retrieval
|
|
# =====================
|
|
RETRIEVER_TOP_K=10
|
|
SIMILARITY_THRESHOLD=0.3
|
|
|
|
# =====================
|
|
# Data Directories
|
|
# =====================
|
|
RAW_DATA_DIR=data/raw
|
|
PROCESSED_DATA_DIR=data/processed
|
|
NOTE_UPLOAD_DIR=data/notes
|
|
|
|
# =====================
|
|
# Metadata / Payload
|
|
# =====================
|
|
DEFAULT_BOOK_DOMAIN=computer_science
|
|
BOOK_PAYLOAD_TYPE=book_content
|
|
NOTE_PAYLOAD_TYPE=personal_note
|
|
|
|
# =====================
|
|
# Future Partition (reserved)
|
|
# 当前数据量较小,Payload过滤已足够,默认关闭。
|
|
# =====================
|
|
VALID_DOMAINS=computer_science,literature,history,philosophy
|
|
ENABLE_PARTITION=false
|
|
AUTO_MIGRATE_MILVUS_SCHEMA=true
|
|
STRICT_BOOK_METADATA_WRITE=true
|
|
|
|
# =====================
|
|
# Logging
|
|
# =====================
|
|
LOG_LEVEL=INFO
|