Пікірлер
@zacharyzheng9326 5 сағат бұрын
用免费的groq，支持所有模型甚至llama-3.2-90b-vison，支持所有开发语言甚至PHP
@周復佑 8 сағат бұрын
2:35 正文开始~
@vincentn1371 8 сағат бұрын
👍👍👍
@AIsuperdomain 8 сағат бұрын
谢谢支持🤝🤝
@天堂超我 8 сағат бұрын
謝謝你發佈視頻，對於視頻中講述的兩個工作流，可以導出工作流提供下載嗎？
@coolmv 10 сағат бұрын
很详细的教程
@AIsuperdomain 10 сағат бұрын
谢谢支持🤝🤝
@良张-v2r 14 сағат бұрын
老大请问Claude Dev 支持用中文输入propmt实现编程吗？
@manyaccscom Күн бұрын
这个研究还是很有意义的，但是要实现全天候的自动化,token的消耗成本就太大了，有没有可能使用llama3.2 11b或者90B这种模型来实现这个功能
@AIsuperdomain Күн бұрын
是可以，但是准确率会下降
@manyaccscom Күн бұрын
@@AIsuperdomain 针对特定的重复性的任务可以做微调，像视频里面这种应用需求是面向大众的，需求比较多样化
@hzhikang6304 2 күн бұрын
违反人权和个人隐私，怪不得美帝要封锁你们
@hugo1894 2 күн бұрын
谢谢老师
@GrowthAngels 2 күн бұрын
要是一天24小时的循环任务得花多少钱
@AIsuperdomain 2 күн бұрын
这个得看任务复杂度了，不太好评估24小时能花多少钱
@江生浩 2 күн бұрын
支持下 每期必看
@AIsuperdomain 2 күн бұрын
谢谢支持🤝🤝
@feiyi7237 2 күн бұрын
Haystack 能实现根据query搜索pdf或者搜索音频视频图片吗
@vincentn1371 2 күн бұрын
👍👍👍
@AIsuperdomain 2 күн бұрын
🤝🤝🤝
@HarryGlory-s2g 2 күн бұрын
那么现在问题来了，如何让ai知道它的认知是错误的，从而让它服从命令？
@AIsuperdomain 2 күн бұрын
让它截个图，它看图就知道了
@wumitiyo9754 2 күн бұрын
很早就有autogpt可以通过终端操控电脑吗，这个只是头一个根据图形界面操控，放弃命令改用图形当前的意义并不大
@AIsuperdomain 2 күн бұрын
通过命令有很大的局限性
@AC-pw7rl 2 күн бұрын
那不是重點，重點在於聰明的模型操作電腦能做的事情是不一樣的
@AIsuperdomain 2 күн бұрын
👍👍👍
@SpiritualSagas735 2 күн бұрын
有意思，AI已經會拒絕執行他認為不需要的命令了嗎?
@AIsuperdomain 2 күн бұрын
对，会拒绝的
@王康-w2i 2 күн бұрын
稍微复杂点的项目 他就蒙蔽了 简单的可以用这个玩玩
@zacharyzheng9326 3 күн бұрын
如果不是免费为什么我不用cursers
@殷维杰 3 күн бұрын
cline运行了一会后出现403 {"error":{"type":"forbidden","message":"Request not allowed"}}，不知道有没有碰到过的
@殷维杰 3 күн бұрын
切换梯子节点又好了
@tyronetyrone2652 3 күн бұрын
真的能自动编程吗
@AIsuperdomain 2 күн бұрын
这还不算自动编程？
@conglife 3 күн бұрын
在国内调用claude的api要不要科学上网？
@SandraMares-bs5dw 3 күн бұрын
长文本，大文件这种就不行了。token就不够
@AIsuperdomain 3 күн бұрын
一个文件里有几千行代码？
@jdandrew-n1j 3 күн бұрын
很耗token
@AIsuperdomain 3 күн бұрын
还好吧，整个演示流程才消耗了1美金多
@vincentn1371 3 күн бұрын
👍👍👍
@AIsuperdomain 3 күн бұрын
谢谢支持🤝🤝🤝
@張博文-n6l 3 күн бұрын
關於一開始給ai 的 prompt # ## --do 這種markdown 語法 ai 表現會比較好嗎? 還是沒影響~
@AIsuperdomain 3 күн бұрын
markdown格式效果更好些
@張博文-n6l 3 күн бұрын
@@AIsuperdomain 好,謝謝.目前也是用這個組合搭配vscode
@garfieldlavi 3 күн бұрын
Cline也可以解釋代碼不是嗎ㄓ
@AIsuperdomain 3 күн бұрын
对 可以的
@吕浩源-x1e 3 күн бұрын
太棒了 感谢
@AIsuperdomain 3 күн бұрын
谢谢支持🤝🤝
@liuyang55ailai 5 күн бұрын
感谢UP主。我看了 haystack 中目前并不支持阿里通义千问的API，请问怎么自己去实现呢？
@kironlau 5 күн бұрын
阿里沒openai格式接口嗎？ 應該有的
@liuyang55ailai 4 күн бұрын
@@kironlau 有的，明白了，那就是自己参考haystack 的openai去实现一个阿里的component。谢谢
@宇智波帶土-e1g 5 күн бұрын
pdf的知識可以是中文嗎? 感謝~
@AIsuperdomain 4 күн бұрын
可以
@shenzhang5020 6 күн бұрын
我想知道会员群在哪
@StoryJacky 6 күн бұрын
很好，很详细
@AIsuperdomain 6 күн бұрын
谢谢支持
@lumiseven8630 6 күн бұрын
老师你好, 我想参考下视频后半段的text-to-sql的实例的代码, blog上好像被截断了, 能补全下吗? 谢谢
@wzwc-c3p 6 күн бұрын
是必須下載python嗎?
@wzwc-c3p 6 күн бұрын
代碼學得頭皮發麻,可以不學嗎
@fan6684 6 күн бұрын
notebooklm 和 Haystack 对比有区别吗？🤔
@AIsuperdomain 6 күн бұрын
有区别，等我出一期对比视频
@張博文-n6l 4 күн бұрын
差不少,notebooklm很笨,主要我猜應該是 google用的ai model 給免費使用者都是用比較弱的 不是gemini pro
@mash-room 7 күн бұрын
Kotaemon 我是透過安裝包下載的，我設置了用 ollama embed 和聊天，但上傳了文檔它一直說我error無法回答任何東西也無法嵌入
@AIsuperdomain 7 күн бұрын
发下报错日志，我帮你看看
@mash-room 7 күн бұрын
@@AIsuperdomain Session reasoning type None Session LLM None Reasoning class <class 'ktem.reasoning.simple.FullQAPipeline'> Reasoning state {'app': {'regen': False}, 'pipeline': {}} Thinking ... Retrievers [DocumentRetrievalPipeline(DS=<kotaemon.storages.docstores.lancedb.LanceDBDocumentStore object at 0x000001E284331DB0>, FSPath=WindowsPath('D:/20240916-Kotaemon/kotaemon-app/ktem_app_data/user_data/files/index_1'), Index=<class 'ktem.index.file.index.IndexTable'>, Source=<class 'ktem.index.file.index.Source'>, VS=<kotaemon.storages.vectorstores.chroma.ChromaVectorStore object at 0x000001E284332050>, get_extra_table=False, llm_scorer=LLMTrulensScoring(concurrent=True, normalize=10, prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x000001E286A30E50>, system_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x000001E286A32800>, top_k=3, user_prompt_template=<kotaemon.llms.prompts.template.PromptTemplate object at 0x000001E286A32BF0>), mmr=False, rerankers=[CohereReranking(cohere_api_key='', model_name='rerank-multilingual-v2.0')], retrieval_mode='hybrid', top_k=10, user_id=1), GraphRAGRetrieverPipeline(DS=<theflow.base.unset_ object at 0x000001E2EB6EC220>, FSPath=<theflow.base.unset_ object at 0x000001E2EB6EC220>, Index=<class 'ktem.index.file.index.IndexTable'>, Source=<theflow.base.unset_ object at 0x000001E2EB6EC220>, VS=<theflow.base.unset_ object at 0x000001E2EB6EC220>, file_ids=[], user_id=<theflow.base.unset_ object at 0x000001E2EB6EC220>)] searching in doc_ids ['4299411a-78cc-4d17-b7bb-8d1f59b7d9a8'] retrieval_kwargs: dict_keys(['do_extend', 'scope', 'filters']) Traceback (most recent call last): File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\queueing.py", line 575, in process_events response = await route_utils.call_process_api( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio oute_utils.py", line 276, in call_process_api output = await app.get_blocks().process_api( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\blocks.py", line 1923, in process_api result = await self.call_function( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\blocks.py", line 1520, in call_function prediction = await utils.async_iteration(iterator) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\utils.py", line 663, in async_iteration return await iterator.anext() File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\utils.py", line 656, in anext return await anyio.to_thread.run_sync( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\anyio_backends_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\anyio_backends_asyncio.py", line 859, in run result = context.run(func, *args) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\utils.py", line 639, in run_sync_iterator_async return next(iterator) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\gradio\utils.py", line 801, in gen_wrapper response = next(iterator) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\ktem\pages\chat_init_.py", line 804, in chat_fn for response in pipeline.stream(chat_input, conversation_id, chat_history): File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\ktem easoning\simple.py", line 660, in stream docs, infos = self.retrieve(message, history) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\ktem easoning\simple.py", line 488, in retrieve retriever_docs = retriever_node(text=query) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1097, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1088, in call output = self.fl.exec(func, args, kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\backends\base.py", line 151, in exec return run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 144, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 141, in call _output = self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 117, in call return self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1017, in _runx return self.run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\ktem\index\file\pipelines.py", line 162, in run docs = self.vector_retrieval(text=text, top_k=self.top_k, **retrieval_kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1261, in exec return child(*args, **kwargs, fl_runstates=fl_runstates) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1097, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1088, in call output = self.fl.exec(func, args, kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\backends\base.py", line 151, in exec return run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 144, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 141, in call _output = self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 117, in call return self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1017, in _runx return self.run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\kotaemon\indices\vectorindex.py", line 188, in run emb = self.embedding(text)[0].embedding File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1261, in exec return child(*args, **kwargs, fl_runstates=fl_runstates) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1675, in call return self.create_callable(getattr(self.ff_original_obj, "call"))( File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1663, in wrapper raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1661, in wrapper output = callable_obj(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 144, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 141, in call output = self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 117, in call return self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1261, in exec return child(*args, **kwargs, fl_runstates=fl_runstates) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1097, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1088, in call output = self.fl.exec(func, args, kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\backends\base.py", line 151, in exec return run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 144, in call raise e from None File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 141, in call output = self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\middleware.py", line 117, in call return self.next_call(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\theflow\base.py", line 1017, in runx return self.run(*args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\kotaemon\embeddings\base.py", line 10, in run return self.invoke(text, *args, **kwargs) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\kotaemon\embeddings\openai.py", line 104, in invoke resp = self.openai_response(client, input=input, **kwargs).dict() File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\tenacity_init.py", line 289, in wrapped_f return self(f, *args, **kw) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\tenacity_init.py", line 379, in call do = self.iter(retry_state=retry_state) File "D:\20240916-Kotaemon\kotaemon-app\install_dir\env\lib\site-packages\tenacity_init.py", line 326, in iter raise retry_exc from fut.exception() tenacity.RetryError: RetryError[<Future at 0x1e286782500 state=finished raised AuthenticationError>]
@AIsuperdomain 7 күн бұрын
尝试在设置中关闭OpenAI，开启ollama
@mash-room 5 күн бұрын
@@AIsuperdomain 開了
@clee6968 7 күн бұрын
請教一下，haystack有辦法結合llamaindex寫成agentic RAG嗎？ 謝謝🙏
@AIsuperdomain 7 күн бұрын
可以的 等我出一期视频详细演示
@clee6968 7 күн бұрын
@@AIsuperdomain 太期待了😊
@張博文-n6l 7 күн бұрын
如果用docker安裝 docke kotaemon 執行的時候 會跳到 要輸入帳號密碼~ 搞了我老半天 想說我都沒註冊哪來帳號密碼 研究後帳號密碼預設 都是 admin 這樣就可以用了~~
@AIsuperdomain 7 күн бұрын
👍👍👍
@vincentn1371 7 күн бұрын
👍👍👍
@AIsuperdomain 7 күн бұрын
谢谢支持
@wumitiyo9754 7 күн бұрын
Haystack看演示的只是把一个txt建立的知识库，支持多个pdf建立一个知识库吗每次添加新的内容进去是不是要全部重建，还是如果要多本书就要建立多个知识库，用同一个提示词全部检索一遍，
@AIsuperdomain 7 күн бұрын
支持多文档建立知识库
@陳柏均-d4q 7 күн бұрын
您好，請問會更新新版的ragas影片嗎?前陣子剛更新
@enigma162 7 күн бұрын
这个付费的API价格贵吗？从来没用过这种充值付费的，一直买的包月的GPT
@marschuang1977 7 күн бұрын
感謝分享👍 想請問Haystack是否有支持中文知識檢索？
@AIsuperdomain 7 күн бұрын
支持中文
@marschuang1977 7 күн бұрын
@@AIsuperdomain 謝謝回覆
@侯章祥 7 күн бұрын
感謝分享
@AIsuperdomain 7 күн бұрын
谢谢支持🤝🤝
@陳小良-n6c 7 күн бұрын
感謝分享
@AIsuperdomain 7 күн бұрын
谢谢支持🤝🤝🤝
@zirizhao3606 7 күн бұрын
谢谢播主的分享，让我受用无穷！
@AIsuperdomain 7 күн бұрын
感谢支持🤝🤝
@feiyi7237 7 күн бұрын
这么几个东西，aider gptme open-interpreter 这三个东西看起来功能是一样的，它们的区别是啥呢？如果我只掌握一个可以吗
@rosszhu1660 7 күн бұрын
已被证明是骗子
@clifflin7149 8 күн бұрын
这个注册不了吧，必须要公司businss ID
@taojiang73 8 күн бұрын
问一下，Data下那两个文件哪里可以下载到。
@jz1818 9 күн бұрын
想問一下這樣搜索openai 花了多少美元?