{"id":3523,"date":"2026-10-18T09:28:23","date_gmt":"2026-10-18T14:28:23","guid":{"rendered":"https:\/\/xlinesoft.com\/blog\/?p=3523"},"modified":"2026-10-18T10:29:56","modified_gmt":"2026-10-18T15:29:56","slug":"add-semantic-search-to-a-phprunner-application","status":"publish","type":"post","link":"https:\/\/xlinesoft.com\/blog\/2026\/10\/18\/add-semantic-search-to-a-phprunner-application\/","title":{"rendered":"Add Semantic Search to a PHPRunner Application"},"content":{"rendered":"

Keyword search can miss records that describe the same problem using different words. In this tutorial, we will add semantic search to a PHPRunner support-ticket application. A search for ‘customers having access or login problems’ can find tickets about rejected credentials, unauthorized sessions, or account access even when they do not contain the exact search phrase.<\/p>\n

The application uses the OpenAI Embeddings API to convert ticket text and each search phrase into vectors. PHPRunner then compares those vectors locally with cosine similarity and returns the 30 closest tickets. This approach is intended for relatively small collections. For tens of thousands of records or more, use a vector database instead of comparing every vector in PHP. The cosine similarity scores in the diagram measure how closely the vectors are related. They are not probabilities or percentages of correctness.<\/p>\n

\"\"<\/a>
\n<\/p>\n

Semantic Search in Action<\/strong><\/p>\n

Let’s try searching for “Employees are being denied entry to the company portal.”<\/strong><\/p>\n

Notice that the results include tickets about failed logins, incorrect credentials, authentication errors, and users being redirected back to the sign-in page.<\/p>\n

These tickets describe similar problems using different terminology. A traditional keyword search might miss some of them because the search phrase doesn’t contain words such as “password,” “login,” or “authentication.”<\/p>\n

Semantic search recognizes the relationship between these descriptions and returns relevant tickets based on their meaning, not just matching words.<\/p>\n

The application uses cosine similarity to rank the results, displaying the most relevant tickets first. Click the screenshot to see the exact search phrase and the results it returns. <\/p>\n

\"\"<\/a><\/p>\n

How the search works:<\/strong><\/p>\n

    \n
  1. Each ticket’s subject and description are converted into an embedding vector.<\/li>\n
  2. The vector is stored in the database with the ticket.<\/li>\n
  3. The user’s search phrase is converted into a vector with the same embedding model.<\/li>\n
  4. The generated PHP application calculates cosine similarity between the query vector and the stored ticket vectors.<\/li>\n
  5. The most relevant tickets are returned in similarity order.<\/li>\n<\/ol>\n

    When a ticket is added or its searchable text changes, its subject and description are sent to the OpenAI Embeddings API. During a normal search, only the user’s search phrase is sent. Existing ticket vectors remain in the local database and are reused. OpenAI creates the vectors but does not search the ticket table; the similarity calculations happen locally in the generated PHP application.<\/p>\n

    1. Creating the support tickets table<\/h3>\n

    Create the following MySQL table and add it to the PHPRunner project.<\/p>\n

    \n