tantivy

import tantivy import os # 1. Declare the schema schema_builder = tantivy.SchemaBuilder() schema_builder.add_text_field("title", stored=True, tokenizer_name="default") schema_builder.add_text_field("body", stored=True, tokenizer_name="default") schema_builder.add_integer_field("doc_id", stored=True, indexed=True) schema = schema_builder.build() # 2. Create an in-memory index (for persistent, specify a path) # To use a persistent index, use: index = tantivy.Index(schema, path="/tmp/my_index") index = tantivy.Index(schema) # 3. Get an index writer and add documents writer = index.writer(50_000_000) # 50MB memory arena writer.add_document(tantivy.Document(title=["The Old Man and the Sea"], body=["He was an old man who fished alone in a skiff."], doc_id=[1])) writer.add_document(tantivy.Document(title=["The Great Gatsby"], body=["In my younger and more vulnerable years my father gave me some advice."], doc_id=[2])) writer.commit() # 4. Get a reader and searcher index.reload() reader = index.reader() searcher = reader.searcher() # 5. Build and execute a query query_parser = tantivy.QueryParser(schema, default_fields=["title", "body"]) query = query_parser.parse_query("old man") hits = searcher.search(query, 10) # 6. Retrieve documents print("Search results:") for score, doc_address in hits: retrieved_doc = searcher.doc(doc_address) print(f" Score: {score:.2f}, Doc ID: {retrieved_doc['doc_id'][0]}, Title: {retrieved_doc['title'][0]}") # Example of retrieving a non-existent field (will be empty list) missing_field = retrieved_doc.get('non_existent_field') print(f" Non-existent field for last doc: {missing_field}") # Expected: []