Query text
Stay organized with collections
Save and categorize content based on your preferences.
Find the indexed files that are the most similar to the query text.
Explore further
For detailed documentation that includes this code sample, see the following:
Code sample
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],[],[],[],null,["# Query text\n\nFind the indexed files that are the most similar to the query text.\n\nExplore further\n---------------\n\n\nFor detailed documentation that includes this code sample, see the following:\n\n- [Content Classification Tutorial](/natural-language/docs/classify-text-tutorial)\n\nCode sample\n-----------\n\n### Python\n\n\nTo learn how to install and use the client library for Natural Language, see\n[Natural Language client libraries](/natural-language/docs/reference/libraries).\n\n\nFor more information, see the\n[Natural Language Python API\nreference documentation](/python/docs/reference/language/latest).\n\n\nTo authenticate to Natural Language, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n def query(index_file, text, n_top=3):\n \"\"\"Find the indexed files that are the most similar to\n the query text.\n \"\"\"\n\n with open(index_file) as f:\n index = json.load(f)\n\n # Get the categories of the query text.\n query_categories = classify(text, verbose=False)\n\n similarities = []\n for filename, categories in index.items():\n similarities.append((filename, similarity(query_categories, categories)))\n\n similarities = sorted(similarities, key=lambda p: p[1], reverse=True)\n\n print(\"=\" * 20)\n print(f\"Query: {text}\\n\")\n for category, confidence in query_categories.items():\n print(f\"\\tCategory: {category}, confidence: {confidence}\")\n print(f\"\\nMost similar {n_top} indexed texts:\")\n for filename, sim in similarities[:n_top]:\n print(f\"\\tFilename: {filename}\")\n print(f\"\\tSimilarity: {sim}\")\n print(\"\\n\")\n\n return similarities\n\nWhat's next\n-----------\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=language)."]]