84 lines
3.4 KiB
C#
84 lines
3.4 KiB
C#
using System.Net.Http.Headers;
|
|
using System.Text.Json;
|
|
using System.Text.Json.Serialization;
|
|
|
|
using Toak.Api.Models;
|
|
using Toak.Serialization;
|
|
|
|
namespace Toak.Api;
|
|
|
|
public class GroqApiClient
|
|
{
|
|
private readonly HttpClient _httpClient;
|
|
|
|
public GroqApiClient(string apiKey)
|
|
{
|
|
_httpClient = new HttpClient();
|
|
_httpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", apiKey);
|
|
_httpClient.BaseAddress = new Uri("https://api.groq.com/openai/v1/");
|
|
}
|
|
|
|
public async Task<string> TranscribeAsync(string filePath, string language = "", string model = "whisper-large-v3-turbo")
|
|
{
|
|
using var content = new MultipartFormDataContent();
|
|
using var fileStream = File.OpenRead(filePath);
|
|
using var streamContent = new StreamContent(fileStream);
|
|
|
|
streamContent.Headers.ContentType = new MediaTypeHeaderValue("audio/wav"); // or mpeg
|
|
content.Add(streamContent, "file", Path.GetFileName(filePath));
|
|
|
|
string modelToUse = string.IsNullOrWhiteSpace(model) ? "whisper-large-v3-turbo" : model;
|
|
|
|
// according to docs whisper-large-v3-turbo requires the language to be provided if it is to be translated later potentially or if we need the most accurate behavior
|
|
// Actually, if we want language param, we can pass it to either model
|
|
content.Add(new StringContent(modelToUse), "model");
|
|
|
|
if (!string.IsNullOrWhiteSpace(language))
|
|
{
|
|
var firstLang = language.Split(',')[0].Trim();
|
|
content.Add(new StringContent(firstLang), "language");
|
|
}
|
|
|
|
var response = await _httpClient.PostAsync("audio/transcriptions", content);
|
|
|
|
if (!response.IsSuccessStatusCode)
|
|
{
|
|
var error = await response.Content.ReadAsStringAsync();
|
|
throw new Exception($"Whisper API Error: {response.StatusCode} - {error}");
|
|
}
|
|
|
|
var json = await response.Content.ReadAsStringAsync();
|
|
var result = JsonSerializer.Deserialize(json, AppJsonSerializerContext.Default.WhisperResponse);
|
|
return result?.Text ?? string.Empty;
|
|
}
|
|
|
|
public async Task<string> RefineTextAsync(string rawTranscript, string systemPrompt, string model = "openai/gpt-oss-20b")
|
|
{
|
|
var requestBody = new LlamaRequest
|
|
{
|
|
Model = string.IsNullOrWhiteSpace(model) ? "openai/gpt-oss-20b" : model,
|
|
Temperature = 0.0,
|
|
Messages = new[]
|
|
{
|
|
new LlamaRequestMessage { Role = "system", Content = systemPrompt },
|
|
new LlamaRequestMessage { Role = "user", Content = $"<transcript>{rawTranscript}</transcript>" }
|
|
}
|
|
};
|
|
|
|
var jsonContent = new StringContent(JsonSerializer.Serialize(requestBody, AppJsonSerializerContext.Default.LlamaRequest), System.Text.Encoding.UTF8, "application/json");
|
|
|
|
var response = await _httpClient.PostAsync("chat/completions", jsonContent);
|
|
|
|
if (!response.IsSuccessStatusCode)
|
|
{
|
|
var error = await response.Content.ReadAsStringAsync();
|
|
throw new Exception($"Llama API Error: {response.StatusCode} - {error}");
|
|
}
|
|
|
|
var json = await response.Content.ReadAsStringAsync();
|
|
var result = JsonSerializer.Deserialize(json, AppJsonSerializerContext.Default.LlamaResponse);
|
|
|
|
return result?.Choices?.FirstOrDefault()?.Message?.Content ?? string.Empty;
|
|
}
|
|
}
|