Ollama is not responding to Open WebUI when Indexing codebase

[danielaskdd]

Before submitting your bug report

• I believe this is a bug. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS:Macos Sequoia 15.2 intel Core i9
- Continue version: 0.9.248
- IDE version: Vscode 1.96.2
- Model: - (Model from Ollama or Open WebUI in local network)
- config.json:
  
{
  "models": [
    {
      "title": "Qwen-coder-7b",
      "provider": "ollama",
      "model": "qwen2.5-coder:7b",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "http://m4.lan.xxxxxx.com:11434"
    },
    {
      "title": "Deepseek-coder",
      "provider": "openai",
      "model": "deepseek-coder",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "https://ai.xxxxxx.com:5013/api",
      "useLegacyCompletionsEndpoint": false,
      "apiKey": "sk-api-key"
    },
    {
      "title": "Claude3.5 Sonnet",
      "provider": "openai",
      "model": "anthropic/claude-3.5-sonnet:beta",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "https://ai.xxxxxx.com:5013/api",
      "useLegacyCompletionsEndpoint": false,
      "apiKey": "sk-api-key"
    },
    {
      "title": "o1-mini",
      "provider": "openai",
      "model": "o1-mini",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "https://ai.xxxxxx.com:5013/api",
      "useLegacyCompletionsEndpoint": false,
      "apiKey": "sk-api-key"
    },
    {
      "title": "gpt-4o",
      "provider": "openai",
      "model": "gpt-4o",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "https://ai.xxxxxx.com:5013/api",
      "useLegacyCompletionsEndpoint": false,
      "apiKey": "sk-api-key"
    },
    {
      "title": "Qwen-Coder-Plus",
      "provider": "openai",
      "model": "qwen-coder-plus",
      "systemMessage": "Speak Chinese. When generating commit message, write in Chinese.",
      "apiBase": "https://ai.xxxxxx.com:5013/api",
      "useLegacyCompletionsEndpoint": false,
      "apiKey": "sk-api-key"
    }
],
  "embeddingsProvider": {
    "title": "BGE-M3",
    "provider": "ollama",
    "model": "bge-m3:latest",
    "apiBase": "http://m4.lan.xxxxxx.com:11434"
  },
  "tabAutocompleteModel": {
    "title": "Tab Autocomplete",
    "provider": "ollama",
    "model": "qwen2.5-coder:1.5b",
    "apiBase": "http://m4.lan.xxxxxx.com:11434"
  },
  "reranker": {
    "name": "voyage",
    "params": {
      "model": "rerank-2",
      "apiKey": "pa-api-key"
    }
  },
  "customCommands": [
    {
      "name": "explain",
      "prompt": "{{{ input }}}\n\n使用中文详细解释所选代码。详细说明其功能、用途和工作原理。",
      "description": "解释代码"
    },
    {
      "name": "check",
      "prompt": "{{{ input }}}\n\n检查选定代码的语法和逻辑错误，如果有明显可以优化的地方，请给出优化建议。使用中文回答问题。",
      "description": "检查代码错误和提出优化建议"
    },
    {
      "name": "test",
      "prompt": "{{{ input }}}\n\n为选定的代码编写一套完整的单元测试代码。测试需要包含重要边界情况的正确性检查。测试需要包括测试前的准备和测试后的清理工作。使用中文书写代码备注",
      "description": "编写单元测试代码"
    }
  ],
  "contextProviders": [
    {
      "name": "code",
      "params": {}
    },
    {
      "name": "docs",
      "params": {}
    },
    {
      "name": "diff",
      "params": {}
    },
    {
      "name": "terminal",
      "params": {}
    },
    {
      "name": "problems",
      "params": {}
    },
    {
      "name": "folder",
      "params": {}
    },
    {
      "name": "web",
      "params": {}
    },
    {
      "name": "codebase",
      "params": {}
    }
  ],
  "slashCommands": [
    {
      "name": "share",
      "description": "Export the current chat session to markdown"
    },
    {
      "name": "cmd",
      "description": "Generate a shell command"
    },
    {
      "name": "commit",
      "description": "Generate a git commit message"
    }
  ]
}

Description

There are the following issues with indexing a codebase containing hundreds of files:

1. The indexing progress is extremely slow. During indexing, Ollama cannot respond to requests from other clients. After indexing is completed, Ollama resumes normal operation.
2. During indexing, Ollama receives a large number of aip/embed requests, and the processing time for each request is very long, ranging from 1 to 7 minutes.
3. During indexing, clicking the "Cancel Indexing" button on the plugin UI is ineffective.

Causing Ollama to be unresponsive to other clients' requests is a very serious problem, resulting in all AI clients in the company being suspended.

To reproduce

1. open a folder with hundreds of source code files with VScode.
2. wait for the codebase index start

Log output

No response