From 8d57e593f845eda6cc4d97546f331b53f543f0f4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=BA=B7=E5=AE=87=E4=BD=B3?= Date: Fri, 13 Jun 2025 15:25:37 +0800 Subject: [PATCH] =?UTF-8?q?=E5=90=88=E5=B9=B6=E5=88=86=E6=94=AF?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * Merge branch 'main' into feature/modal-cluster-gemini * FIX 修复拼接网格图的异步失效问题 * FIX 修复拼接网格图的异步失效问题 * Merge branch 'main' into feature/modal-cluster-gemini * Merge branch 'main' into feature/modal-cluster-gemini * FIX 调高合成网格图容器配置 * Merge branch 'main' into feature/modal-cluster-gemini * FIX 修复带图片模态推理接口 * PERF 优化Gemini Prompt词 * Merge remote-tracking branch 'origin/main' into feature/modal-cluster-gemini * ADD 增加网格图片创建接口 ADD gemini推理打点增加商品封面模态 PERF gemini打点结果相邻时间线同商品合并 * Merge branch 'main' into feature/modal-cluster-gemini * FIX 429重试机制 * FIX 修复Gemini推理函数入参 * Merge branch 'main' into feature/modal-cluster-gemini * PERF gemini修改参数类型 ADD 增加批量删除Gemini文件接口 * PERF gemini修改prompt * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF gemini修改prompt * 录制HLS时 结果复制到S3挂载点增加一个fallback处理 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF gemini修改prompt * PERF gemini增加图像模态 * PERF gemini增加图像模态 * fix : TikHub的Logger换为Loguru * fix : 修复直播切分视频接口 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF tikhub接口增加随机延迟 * Merge remote-tracking branch 'origin/feature/modal-cluster' into feature/modal-cluster * 合并分支 * fix : hls录制缓存读写问题 * FIX 修改冲突 * ADD 增加获取直播间指定商品数量接口 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF 修改tikhub到aws * fix : 增加s3分片上传接口 * PERF Gemini推理直接从参数列表获取商品列表 ADD Tikhub增加获取置顶|讲解中商品接口 * PERF Gemini推理直接从参数获取商品列表 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * fix 处理jpg图片的codec_name应为mjpg * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF 优化返回值 * fix 获取媒体metadata的类型报错，modal client升级到1.0.2 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF 风控后爬虫直接退出避免cookie失效 PERF 分离tikhub api, 使用更低的保持时间以更换IP FIX 修复Dict键不存在报错的bug * fix 一些webhook相关的bug，添加了更详细的接口说明 * 更新直播录制为可跳转时间的hls流接口，用于替代掉腾讯VOD+火山云拉流转推，片段保证每片开头为关键帧，时间精度准确到毫秒级 * ADD 增加直播间商品增量缓存触发器 * Merge branch 'feature/modal-cluster' into feature/modal-cluster-gemini * PERF 调整gemini prompt * - KVCache类改为可拓展，基于环境变量设置KV space - test 环境配置与CF测试环境对齐 * FIX 修复Gemini推理视频切条的问题 PERF 优化视频切条函数性能 * ADD 基本完成gemini视频推理API * ADD 添加内联的tikhub * 对齐预发环境 --------- Merge request URL: https://g-ldyi2063.coding.net/p/dev/d/modalDeploy/git/merge/4799 Co-authored-by: 康宇佳，shuohigh@gmail.com --- src/cluster/video_apps/make_grid_upload.py | 67 +++++++++++----------- 1 file changed, 34 insertions(+), 33 deletions(-) diff --git a/src/cluster/video_apps/make_grid_upload.py b/src/cluster/video_apps/make_grid_upload.py index e75c526..66df8dd 100644 --- a/src/cluster/video_apps/make_grid_upload.py +++ b/src/cluster/video_apps/make_grid_upload.py @@ -45,40 +45,8 @@ with downloader_image.imports(): :return: 图片路径 """ try: - cell_height = image_size + text_height - cell_width = image_size - # 提取图片路径和文字说明 - image_paths = [] - captions = [] - for info in image_info_list: - captions.append(info["title"]) - if "resize:200" in info["cover"]: - info["cover"] = info["cover"].replace("resize:200", f"resize:{image_size}") - image_paths.append(info["cover"]) - - # 检查输入 - if len(image_paths) != len(captions): - raise ValueError("图片数量与文字说明数量不匹配") - - # 处理图片（包括从网络获取） - loaded_images = [] - for path in image_paths: - if path.startswith(('http://', 'https://')): - try: - response = requests.get(path) - response.raise_for_status() - img = Image.open(BytesIO(response.content)) - loaded_images.append(img) - except requests.RequestException as e: - raise FileNotFoundError(f"无法从网络获取图片: {path}, 错误: {e}") - elif os.path.exists(path): - img = Image.open(path) - loaded_images.append(img) - else: - raise FileNotFoundError(f"找不到图片文件: {path}") - # 计算网格大小 - n = len(image_paths) + n = len(image_info_list) max_cols = min(4, n) # 最大列数为6或图片数量 min_rows = math.ceil(n / max_cols) # 最小行数 @@ -100,6 +68,39 @@ with downloader_image.imports(): if best_rows > 4 or best_cols > 4: raise ValueError(f"图片数量({n})过多，无法在4x4网格内合理展示") + cell_height = image_size + text_height + cell_width = image_size + # 提取图片路径和文字说明 + image_paths = [] + captions = [] + for info in image_info_list: + captions.append(info["title"]) + if "resize:200" in info["cover"]: + info["cover"] = info["cover"].replace("resize:200", f"resize:{image_size}") + image_paths.append(info["cover"]) + + # 检查输入 + if len(image_paths) != len(captions): + raise ValueError("图片数量与文字说明数量不匹配") + + # 处理图片（包括从网络获取） + loaded_images = [] + for path in image_paths: + if path.startswith(('http://', 'https://')): + try: + async with httpx.AsyncClient(timeout=60) as client: + response = await client.get(path) + response.raise_for_status() + img = Image.open(BytesIO(response.content)) + loaded_images.append(img) + except requests.RequestException as e: + raise FileNotFoundError(f"无法从网络获取图片: {path}, 错误: {e}") + elif os.path.exists(path): + img = Image.open(path) + loaded_images.append(img) + else: + raise FileNotFoundError(f"找不到图片文件: {path}") + # 创建画布 canvas_width = best_cols * (cell_width + separator) - separator canvas_height = best_rows * (cell_height + separator) - separator