LLM reel caption and video description + Refactor in services

2025-06-30 16:14:29 +02:00
parent 21abbcdff5
commit 228d67a48d
20 changed files with 575 additions and 151 deletions
--- a/app/Services/AIPrompt/OpenAPIPrompt.php
+++ b/app/Services/AIPrompt/OpenAPIPrompt.php
@ -0,0 +1,137 @@
+<?php
+
+namespace App\Services\AIPrompt;
+
+use Uri;
+
+/**
+ * Use OpenAI API to get answers from a model.
+ */
+class OpenAPIPrompt implements IAIPrompt
+{
+    private string $host;
+    private ?string $token = null;
+
+    public function __construct(string $host = null) {
+        $this->host = $host ?? config('llm.api.host');
+        if (config('llm.api.token')) {
+            $this->token = config('llm.api.token');
+        }
+    }
+
+    private function getHeaders(): array
+    {
+        return [
+            'Authorization: ' . ($this->token ? 'Bearer ' . $this->token : ''),
+            'Content-Type: application/json',
+        ];
+    }
+
+    /**
+     * Call the OpenAI API with the given endpoint and body.
+     * @param string $endpoint
+     * @param string $body
+     * @throws \Exception
+     * @return string
+     */
+    private function callAPI(string $endpoint, string $body): string
+    {
+        $url = $this->host . $endpoint;
+
+        $ch = curl_init($url);
+        curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
+        curl_setopt($ch, CURLOPT_HTTPHEADER, $this->getHeaders());
+        curl_setopt($ch, CURLOPT_POST, true);
+        curl_setopt($ch, CURLOPT_POSTFIELDS, $body);
+        $response = curl_exec($ch);
+        $httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
+        curl_close($ch);
+
+        if ($httpCode !== 200) {
+            throw new \Exception("Error calling OpenAI API: HTTP $httpCode - $response");
+        }
+        return $response;
+    }
+
+    /**
+     * Call the OpenAI API generate endpoint. to generate a response to a prompt.
+     * @param string $model
+     * @param string $prompt
+     * @param array $images
+     * @return void
+     */
+    public function generate(string $model, string $prompt, array $images = [], string $outputFormat = null, string $systemMessage = null, bool $keepAlive = true, bool $shouldThink = false): string
+    {
+        /*
+            Generate a completion
+
+            POST /api/generate
+
+            Generate a response for a given prompt with a provided model. This is a streaming endpoint, so there will be a series of responses. The final response object will include statistics and additional data from the request.
+            Parameters
+
+                model: (required) the model name
+                prompt: the prompt to generate a response for
+                suffix: the text after the model response
+                images: (optional) a list of base64-encoded images (for multimodal models such as llava)
+                think: (for thinking models) should the model think before responding?
+
+            Advanced parameters (optional):
+
+                format: the format to return a response in. Format can be json or a JSON schema
+                options: additional model parameters listed in the documentation for the Modelfile such as temperature
+                system: system message to (overrides what is defined in the Modelfile)
+                template: the prompt template to use (overrides what is defined in the Modelfile)
+                stream: if false the response will be returned as a single response object, rather than a stream of objects
+                raw: if true no formatting will be applied to the prompt. You may choose to use the raw parameter if you are specifying a full templated prompt in your request to the API
+                keep_alive: controls how long the model will stay loaded into memory following the request (default: 5m)
+                context (deprecated): the context parameter returned from a previous request to /generate, this can be used to keep a short conversational memory
+
+            Structured outputs
+
+            Structured outputs are supported by providing a JSON schema in the format parameter. The model will generate a response that matches the schema. See the structured outputs example below.
+            JSON mode
+
+            Enable JSON mode by setting the format parameter to json. This will structure the response as a valid JSON object. See the JSON mode example below.
+
+            Important
+
+            **It's important to instruct the model to use JSON in the prompt. Otherwise, the model may generate large amounts whitespace.**
+        */
+
+        // Transform the images to base64
+        foreach ($images as &$image) {
+            if (file_exists($image)) {
+                $image = base64_encode(file_get_contents($image));
+            }
+        }
+
+        $body = [
+            'model' => $model,
+            'prompt' => $prompt,
+            'images' => $images,
+            'think' => $shouldThink,
+            'stream' => false,
+        ];
+
+        if ($systemMessage !== null) {
+            $body['system'] = $systemMessage;
+        }
+        if ($outputFormat !== null) {
+            $body['format'] = json_decode($outputFormat);
+        }
+        if (!$keepAlive) {
+            $body['keep_alive'] = "0m";
+        }
+
+        $body = json_encode($body);
+
+        dump($body);
+        $response = $this->callAPI('/api/generate', $body);
+        $decodedResponse = json_decode($response, true);
+        if (json_last_error() !== JSON_ERROR_NONE) {
+            throw new \Exception("Error decoding JSON response: " . json_last_error_msg());
+        }
+        return $decodedResponse['response'] ?? '';
+    }
+}