OpenAI API Calls

Purpose

Demonstrate two chat OpenAI API calls that can be used in production: (1) Standard Chat Completion for natural-language output, and (2) Function/Tool Call for structured JSON (tool name + arguments). This page explores server-side HTTP requests to the GPT-4o-mini and displays the raw response. **Security note: API key loaded server-side from config outside web root.**

When to choose which:

Standard Chat Completion: When you need narrative text or loose JSON.
Function/Tool: When you need strict args + action execution.

Standard Chat Completion Call

A standard chat completion returns free-form text (you can request JSON-only for formatting but this does not select or execute tools). You ask a question and it answers in natural language. This is ideal for summaries, explanations, and content, but not for executing actions. If you need structure without tools, you can request JSON-only output and parse it yourself, but you won't get a named tool to run.

Output Format

Natural language
JSON-only (use a JSON-only response mode, still no tool selection)

Side Effects

None (you read it and decide what to do)

Use Cases

Summarize long documents, logs, or meetings into tight bullets.
Explain code, stack traces, or concepts in plain English.
Draft copy for emails, help text, release notes, documentation.
Transform text by rewriting the tone, translating, expanding, or condensing.
Light extraction/classification when perfect schema isn't required.

Code Example

Asks the model a question and prints the free-form answer.

PHP

            
              $payload = [
              "model" => "gpt-4o-mini",
              "messages" => [
                ["role" => "user", "content" => "Explain what a schema is in one sentence."]
                ]
              ];

              $ch = curl_init('https://api.openai.com/v1/chat/completions');
              curl_setopt_array($ch, [
                CURLOPT_POST => true,
                CURLOPT_HTTPHEADER => [
                  'Authorization: Bearer ' . $API_KEY,
                  'Content-Type: application/json'
                ],
                CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_SLASHES),
                CURLOPT_RETURNTRANSFER => true,
                CURLOPT_TIMEOUT => 30
              ]);

              $raw = curl_exec($ch);
              curl_close($ch);

              $res = json_decode($raw, true);
              echo htmlspecialchars($res['choices'][0]['message']['content'] ?? 'No content', ENT_QUOTES);

(Enter the access code on the Portfolio page to enable this button.)

Function/Tool Call

A function (tool) call returns a structured payload with function_call.name and function_call.arguments. (It is often called a tool call in newer documentation.) You define a JSON schema describing the tool and the model selects the tool and fills the arguments. Your server interprets that intent and runs code. This is the right choice for command-style actions and backends that require strict, predictable data. The key idea is that the model outputs intent + args and then your code performs the action.

Output Format

function_call.name + function_call.arguments (JSON)

Side Effects

Happen only after your code validates arguments against your schema

Use Cases

Execute actions via backend code such as creating tickets, querying DBs, calling third-party APIs, sending emails, and running CLI (Command Line Interface) tasks.
Fetch structured data with strict arguments (e.g., city, date, limit).
Validate inputs against a JSON schema before touching systems.
Orchestrate workflows where the model selects tools and passes precise arguments.

Code Example

Defines a tool schema and the model returns function_call.name + function_call.arguments.

PHP

            
                $functions = [[
                "name" => "get_current_weather",
                "description" => "Get the current weather in a given location",
                "parameters" => [
                  "type" => "object",
                  "properties" => [
                    "location" => ["type" => "string"],
                    "unit" => ["type" => "string", "enum" => ["celsius","fahrenheit"]]
                  ],
                  "required" => ["location"]
                ]
              ]];

              $payload = [
                "model" => "gpt-4o-mini",
                "messages" => [
                  ["role" => "user", "content" => "What's the weather like in Chicago in celsius?"]
                ],
                "functions" => $functions,
                "function_call" => "auto"
              ];

              $ch = curl_init('https://api.openai.com/v1/chat/completions');
              curl_setopt_array($ch, [
                CURLOPT_POST => true,
                CURLOPT_HTTPHEADER => [
                  'Authorization: Bearer ' . $API_KEY,
                  'Content-Type: application/json'
                ],
                CURLOPT_POSTFIELDS => json_encode($payload, JSON_UNESCAPED_SLASHES),
                CURLOPT_RETURNTRANSFER => true,
                CURLOPT_TIMEOUT => 30
              ]);

              $raw = curl_exec($ch);
              curl_close($ch);

              $res = json_decode($raw, true);
              $msg = $res['choices'][0]['message'] ?? [];
              $fn  = $msg['function_call']['name'] ?? '(none)';
              $args = isset($msg['function_call']['arguments']) ? json_decode($msg['function_call']['arguments'], true) : null;

              echo '<strong>function_call.name:</strong> ' . htmlspecialchars($fn, ENT_QUOTES) . '<br>';
              echo '<strong>function_call.arguments:</strong> <pre>' . htmlspecialchars(json_encode($args, JSON_PRETTY_PRINT|JSON_UNESCAPED_SLASHES), ENT_QUOTES) . '</pre>';

(Enter the access code on the Portfolio page to enable this button.)