chat-ollama

chat-ollama copied to clipboard

I learnt from the OpenAI new update minutes ago, that the upcoming new [GPT-4o](https://openai.com/index/hello-gpt-4o/) by OpenAI is capable for not only text, but also multimedia contents in image, video, audio....

meokey

OpenAI 有个新的功能，[Project](https://help.openai.com/en/articles/9186755-managing-your-work-in-platform-with-projects)，用来区分和管理不同的应用。 如果有时间的话，是否可以加入这个新特性。谢谢。

meokey

wwjCMP

assistant Oops! Response Exception问题

4

assistant Oops! Response Exception 试了llama3-70b,上述这个回答是否是资源不够的问题，下面是ollama的日志 May 10 21:19:13 wae ollama[14972]: {"function":"process_single_task","level":"INFO","line":1507,"msg":"slot data","n_idle_slots":1,"n_processing_slots":0,"task_id":97,"tid":"140514672760704","times tamp":1715347153} May 10 21:19:13 wae ollama[14972]: {"function":"log_server_request","level":"INFO","line":2735,"method":"GET","msg":"request","params":{},"path":"/health","remote_addr":"127.0.0.1","remote_port":57 168,"status":200,"tid":"140473610786560","timestamp":1715347153} May 10 21:19:13 wae ollama[14972]: {"function":"log_server_request","level":"INFO","line":2735,"method":"POST","msg":"request","params":{},"path":"/tokenize","remote_addr":"127.0.0.1","remote_port" :57168,"status":200,"tid":"140473610786560","timestamp":1715347153} May 10 21:19:13...

jingnorth

怎样使用vercel安装chat-ollama？

2

安装报错信息 “Running build in Washington, D.C., USA (East) – iad1 Cloning github.com/geekfranciswong/chat-ollama (Branch: main, Commit: 15dfebc) Cloning completed: 312.525ms Previous build cache not available Running "vercel build" Vercel CLI 34.1.9...

geekfranciswong

错误 fetch failed 如果启用了代理，请确保代理正常工作。知识库添加正常，对话时响应失败

2

嵌入模型：nomic-embed-text:latest 对话模型：llama/llama3:latest URL: /api/models/chat User: null Chat with knowledge base with id: 23 Knowledge base aaa with embedding "nomic-embed-text:latest" Creating embeddings for Ollama served model: nomic-embed-text:latest Creating Chroma vector store...

cylcc06

本地大模型测试结果问题

1

之前测试了本地知识库，发现返回的结果并不理想。想剥离RAG的本地知识库，直接剥离一些数据用上下文的方式测试下是大模型的问题，还是RAG提供的搜索数据的问题。在llama中文社区用llama3-8b测试回答的很理想，各种准确。回来在咱们的系统上不挂本地知识库，用同样的上下文测试llama3-8b-q4,llama2-13b-q4,qwen-4b-q4,结果还是不理想，我的问题是量化4b后模型差距这么大吗？还是ollama调用的模型有什么变化？我们chat-ollama在调用模型时是否有什么特殊的处理？很困扰

jingnorth

参考huggingfists 【知识图谱之从大模型到Neo4j-哔哩哔哩】 https://b23.tv/bgJnFUP

doriszhang2020

本地知识库添加PDF文件报错Error: Chroma getOrCreateCollection error: Error: TypeError: fetch failed

9

运行环境： ChatOllama使用docker compose安装并运行，Ollama使用docker运行。 在Setting中配置本地Ollama的Host：http://host.docker.internal:11434。 操作方法： 登录ChatOllama； 创建本地知识库，Embedding使用Ollama的nomic-embed-text（已下载）； 选择一个PDF文件，点击“save”按钮，查看ChatOllama后台日志，发现报错。 ChatOllama报错日志如下： 2024-04-28 12:21:01 URL: /api/auth/login User: null 2024-04-28 12:21:01 Ollama: { host: 'http://127.0.0.1:11434', username: null, password: null } 2024-04-28 12:21:01 Ollama: {...

NewSNode

请问可以在windows上利用 chat-ollama搭建本地知识库吗？（比如利用gemma大模型）

1

lvlianggan