Manuel/meeting-assistant
Public Access
1
0
Fork 0
Code Issues Pull Requests 4 Actions Packages Projects Releases Wiki Activity Open in Coder

fix: support streaming screenshot OCR

Browse Source
This commit is contained in:
codex
2026-08-03 16:14:01 +02:00
parent b9547ae4c4
commit 5d0ae84426
9 changed files with 362 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files
MeetingAssistant/Screenshots/LiteLlmScreenshotOcrClient.cs
+26 -98
View File
@@ -1,15 +1,13 @@
using System.Net.Http.Headers;
using System.Text;
using System.Text.Json;
using System.Text.Json.Nodes;
using System.Text.RegularExpressions;
using MeetingAssistant.MeetingNotes;
using MeetingAssistant.Summary;
using Microsoft.Extensions.AI;
namespace MeetingAssistant.Screenshots;
public sealed partial class LiteLlmScreenshotOcrClient : IScreenshotOcrClient
{
private static readonly JsonSerializerOptions JsonOptions = new(JsonSerializerDefaults.Web);
private readonly ILogger<LiteLlmScreenshotOcrClient> logger;
private readonly Func<HttpMessageHandler>? httpMessageHandlerFactory;
@@ -40,20 +38,30 @@ public sealed partial class LiteLlmScreenshotOcrClient : IScreenshotOcrClient
: options.Agent.Model;
var key = ResolveApiKey(options);
var imageBytes = await File.ReadAllBytesAsync(screenshotPath, cancellationToken);
using var httpClient = CreateHttpClient();
httpClient.BaseAddress = NormalizeEndpoint(new Uri(endpoint));
httpClient.DefaultRequestHeaders.Authorization = new AuthenticationHeaderValue("Bearer", key);
var payload = CreatePayload(model, CreatePrompt(prompt, imageBytes), imageBytes);
using var content = new StringContent(payload.ToJsonString(JsonOptions), Encoding.UTF8, "application/json");
using var response = await httpClient.PostAsync("responses", content, cancellationToken);
var responseJson = await response.Content.ReadAsStringAsync(cancellationToken);
if (!response.IsSuccessStatusCode)
{
throw new InvalidOperationException(
$"Screenshot OCR request failed with {(int)response.StatusCode} {response.ReasonPhrase}: {responseJson}");
}
var text = ParseOutputText(responseJson);
var httpClient = CreateHttpClient();
httpClient.BaseAddress = LiteLlmResponsesChatClient.NormalizeEndpoint(new Uri(endpoint));
using var chatClient = new LiteLlmResponsesChatClient(
httpClient,
key,
model,
enableThinking: false,
reasoningEffort: "none",
reconnectionAttempts: options.Agent.ReconnectionAttempts,
reconnectionDelay: options.Agent.ReconnectionDelay,
logger: logger,
firstRequestIsUser: false,
useStreaming: options.Agent.UseStreaming);
var response = await chatClient.GetResponseAsync(
[
new ChatMessage(
ChatRole.User,
[
new TextContent(CreatePrompt(prompt, imageBytes)),
new DataContent(imageBytes, "image/png")
])
],
cancellationToken: cancellationToken);
var text = response.Text ?? string.Empty;
logger.LogInformation("Screenshot OCR completed for {ScreenshotPath}", screenshotPath);
return ParseOcrResult(text);
}
@@ -65,35 +73,6 @@ public sealed partial class LiteLlmScreenshotOcrClient : IScreenshotOcrClient
: new HttpClient(httpMessageHandlerFactory());
}
private static JsonObject CreatePayload(string model, string prompt, byte[] imageBytes)
{
return new JsonObject
{
["model"] = model,
["store"] = false,
["input"] = new JsonArray
{
new JsonObject
{
["role"] = "user",
["content"] = new JsonArray
{
new JsonObject
{
["type"] = "input_text",
["text"] = prompt
},
new JsonObject
{
["type"] = "input_image",
["image_url"] = "data:image/png;base64," + Convert.ToBase64String(imageBytes)
}
}
}
}
};
}
private static string CreatePrompt(string prompt, byte[] imageBytes)
{
return TryReadPngDimensions(imageBytes, out var width, out var height)
@@ -210,46 +189,6 @@ public sealed partial class LiteLlmScreenshotOcrClient : IScreenshotOcrClient
bytes[offset + 3];
}
private static string ParseOutputText(string responseJson)
{
using var document = JsonDocument.Parse(responseJson);
var root = document.RootElement;
var parts = new List<string>();
if (root.TryGetProperty("output_text", out var outputText) &&
outputText.ValueKind == JsonValueKind.String &&
!string.IsNullOrWhiteSpace(outputText.GetString()))
{
parts.Add(outputText.GetString()!);
}
if (root.TryGetProperty("output", out var output) && output.ValueKind == JsonValueKind.Array)
{
foreach (var item in output.EnumerateArray())
{
if (!item.TryGetProperty("content", out var content) || content.ValueKind != JsonValueKind.Array)
{
continue;
}
foreach (var block in content.EnumerateArray())
{
if (block.TryGetProperty("type", out var type) &&
type.GetString() == "output_text" &&
block.TryGetProperty("text", out var text) &&
text.ValueKind == JsonValueKind.String &&
!string.IsNullOrWhiteSpace(text.GetString()))
{
parts.Add(text.GetString()!);
}
}
}
}
return parts.Count == 0
? ""
: string.Join(Environment.NewLine + Environment.NewLine, parts);
}
private static string ResolveApiKey(MeetingAssistantOptions options)
{
if (!string.IsNullOrWhiteSpace(options.Screenshots.Ocr.Key))
@@ -278,17 +217,6 @@ public sealed partial class LiteLlmScreenshotOcrClient : IScreenshotOcrClient
$"No screenshot OCR API key configured. Set MeetingAssistant:Screenshots:Ocr:Key or environment variable '{options.Screenshots.Ocr.KeyEnv}'.");
}
private static Uri NormalizeEndpoint(Uri endpoint)
{
var value = endpoint.ToString().TrimEnd('/');
if (!value.EndsWith("/v1", StringComparison.OrdinalIgnoreCase))
{
value += "/v1";
}
return new Uri(value + "/");
}
[GeneratedRegex("```json\\s*(?<json>.*?)\\s*```", RegexOptions.Singleline | RegexOptions.IgnoreCase)]
private static partial Regex JsonCodeBlockRegex();
}