# Minimal install (BM25 + fuzzy only, ~10MB)
pip install "schema-search[postgres]"

# With semantic/hybrid search support (~500MB with PyTorch)
pip install "schema-search[postgres,semantic]"

# With LLM chunking
pip install "schema-search[postgres,semantic,llm]"

# With MCP server
pip install "schema-search[postgres,semantic,mcp]"

# Other databases
pip install "schema-search[mysql,semantic]"      # MySQL
pip install "schema-search[snowflake,semantic]"  # Snowflake
pip install "schema-search[bigquery,semantic]"   # BigQuery
pip install "schema-search[databricks,semantic]" # Databricks

logging:
  level: "WARNING"

embedding:
  location: "memory" # Options: "memory", "vectordb" (coming soon)
  model: "multi-qa-MiniLM-L6-cos-v1"
  metric: "cosine" # Options: "cosine", "euclidean", "manhattan", "dot"
  batch_size: 32
  show_progress: false
  cache_dir: "/tmp/.schema_search_cache"

chunking:
  strategy: "raw" # Options: "raw", "llm"
  max_tokens: 256
  overlap_tokens: 50
  model: "gpt-4o-mini"

search:
  # Search strategy: "semantic" (embeddings), "bm25" (BM25 lexical), "fuzzy" (fuzzy string matching), "hybrid" (semantic + bm25)
  strategy: "bm25"
  initial_top_k: 20
  rerank_top_k: 5
  semantic_weight: 0.67 # For hybrid search (bm25_weight = 1 - semantic_weight)
  hops: 1 # Number of foreign key hops for graph expansion (0-2 recommended)

reranker:
  # CrossEncoder model for reranking. Set to null to disable reranking
  model: null # "Alibaba-NLP/gte-reranker-modernbert-base"

schema:
  include_columns: true
  include_indices: true
  include_foreign_keys: true
  include_constraints: true

output:
  format: "markdown" # Options: "json", "markdown"
  limit: 5 # Default number of results to return

{
  "mcpServers": {
    "schema-search": {
      "command": "uvx",
      "args": [
        "schema-search[postgres,mcp]", 
        "postgresql://user:pass@localhost/db", 
        "optional/path/to/config.yml", 
        "optional llm_api_key", 
        "optional llm_base_url"
      ]
    }
  }
}

{
  "mcpServers": {
    "schema-search": {
      // conda: /Users//opt/miniconda3/envs//bin/schema-search",
      "command": "path/to/schema-search",
      "args": [
        "postgresql://user:pass@localhost/db", 
        "optional/path/to/config.yml", 
        "optional llm_api_key", 
        "optional llm_base_url"
      ]
    }
  }
}

schema-search "postgresql://user:pass@localhost/db" "optional/path/to/config.yml"

from sqlalchemy import create_engine
from schema_search import SchemaSearch

# PostgreSQL
engine = create_engine("postgresql://user:pass@localhost/db")

sc = SchemaSearch(
  engine=engine,
  config_path="optional/path/to/config.yml", # default: config.yml
  llm_api_key="optional llm api key",
  llm_base_url="optional llm base url"
  )

sc.index(force=False) # default is False
results = sc.search("where are user refunds stored?")

# Default output is markdown - render with str()
print(results)  # Formatted markdown with schemas, relationships, and scores

# Access underlying data as dictionary
result_dict = results.to_dict()
for result in result_dict['results']:
    print(result['table'])           # "refund_transactions"
    print(result['schema'])           # Full column info, types, constraints
    print(result['related_tables'])   # ["users", "payments", "transactions"]

# Override output format explicitly
json_results = sc.search("where are user refunds stored?", output_format="json")
print(json_results)  # JSON formatted string

# Override hops, limit, search strategy, and output format
results = sc.search("user_table", hops=1, limit=5, search_type="hybrid", output_format="markdown")

# PostgreSQL
engine = create_engine("postgresql://postgres:mypass@localhost:5432/mydb")

# MySQL
engine = create_engine("mysql+pymysql://root:mypass@localhost:3306/mydb")

# Snowflake
engine = create_engine("snowflake://myuser:mypass@xy12345.us-east-1/MYDB/PUBLIC?warehouse=COMPUTE_WH&role=ANALYST")

# BigQuery
engine = create_engine("bigquery://my-project/my-dataset")

# Databricks
token = "dapi..."
host = "dbc-xyz.cloud.databricks.com"
http_path = "/sql/1.0/warehouses/abc123"
catalog = "main"
schema = "default"  # Optional

# Without schema (queries across all schemas in catalog)
engine = create_engine(
    f"databricks://token:{token}@{host}?http_path={http_path}&catalog={catalog}",
    connect_args={"user_agent_entry": "schema-search"}
)

# With schema (limits to specific schema)
engine = create_engine(
    f"databricks://token:{token}@{host}?http_path={http_path}&catalog={catalog}&schema={schema}",
    connect_args={"user_agent_entry": "schema-search"}
)

# Use fuzzy search instead of default
results = sc.search("user_table", search_type="fuzzy")

# Use BM25 for keyword-based search
results = sc.search("transactions payments", search_type="bm25")

# Use hybrid for best of both worlds
results = sc.search("where are user refunds?", search_type="hybrid")

# Override hops and limit
results = sc.search("user refunds", hops=2, limit=10)  # Expand 2 hops, return 10 tables

# Disable graph expansion
results = sc.search("user_table", hops=0)  # Only direct matches, no foreign key traversal

output:
  format: "markdown"  # or "json"
  limit: 5            # Default number of results

# Default markdown output - just print the object
results = sc.search("user payments")
print(results)  # Formatted markdown

# Access underlying data as dictionary
data = results.to_dict()
print(data['results'][0]['table'])  # "users"

# Override to JSON format
json_results = sc.search("user payments", output_format="json")
print(json_results)  # JSON formatted string

sc = SchemaSearch(
    engine,
    llm_api_key="sk-...",
    llm_base_url="https://api.openai.com/v1/"  # optional
)