Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

@Docs can't index sites anymore #3384

Open
3 tasks done
drrros opened this issue Dec 15, 2024 · 1 comment
Open
3 tasks done

@Docs can't index sites anymore #3384

drrros opened this issue Dec 15, 2024 · 1 comment
Assignees
Labels
area:indexing Relates to embedding and indexing kind:bug Indicates an unexpected problem or unintended behavior "needs-triage"

Comments

@drrros
Copy link

drrros commented Dec 15, 2024

Before submitting your bug report

Relevant environment info

- OS:Rhel 9.5
- Continue version: 0.0.83
- IDE version: PyCharm 2024.3.1
- Model: Qwen2.5-Coder-32B as main model, jina-embeddings-v2-base-code-q8_0.gguf as embeddings model
- config.json:
  
{
  "models": [
    {
      "title": "Qwen2.5-30b",
      "model": "qwen2",
      "contextLength": 32768,
      "apiBase": "http://192.168.0.81:5001",
      "provider": "llama.cpp",
      "apiKey": "qwe",
      "template": "chatml",
      "completionOptions": {
        "maxTokens": 8192
      }
    }
  ],
  "customCommands": [
    {
      "name": "test",
      "prompt": "{{{ input }}}\n\nWrite a comprehensive set of unit tests for the selected code. It should setup, run tests that check for correctness including important edge cases, and teardown. Ensure that the tests are complete and sophisticated. Give the tests just as chat output, don't edit any file.",
      "description": "Write unit tests for highlighted code"
    },
    {
      "name": "review",
      "prompt": "{{{ input }}}\n\nYou are a professional code reviewer. Code review the diff with relation to the existing code. Do not repeat existing code, offer suggestions and optimizations only for code changed in diff. If need, ask for more code.",
      "description": "Code review."
    }
  ],
  "tabAutocompleteModel": {
    "title": "Qwen2.5-Coder-3B",
    "contextLength": 16384,
    "apiBase": "http://192.168.0.81:5002/v1/",
    "provider": "openai",
    "model": "Qwen2.5-Coder-3B",
    "apiKey": "qwe",
    "template": "chatml"
  },
  "tabAutocompleteOptions": {
    "template": "<|fim_prefix|>{{{ prefix }}}<|fim_suffix|>{{{ suffix }}}<|fim_middle|>",
    "multilineCompletions": "auto",
    "maxPromptTokens": 2048
  },
  "contextProviders": [
    {
      "name": "diff",
      "params": {}
    },
    {
      "name": "os"
    },
    {
      "name": "docs"
    },
    {
      "name": "repo-map"
    },
    {
      "name": "url",
      "params": {}
    },
    {
      "name": "code",
      "params": {}
    },
    {
      "name": "terminal",
      "params": {}
    },
    {
      "name": "folder",
      "params": {}
    },
    {
      "name": "codebase",
      "params": {
        "nRetrieve": 50,
        "nFinal": 15,
        "useReranking": true
      }
    },
    {
      "name": "docs",
      "params": {
        "nRetrieve": 25,
        "nFinal": 5,
        "useReranking": true
      }
    }
  ],
  "slashCommands": [
    {
      "name": "edit",
      "description": "Edit selected code"
    },
    {
      "name": "comment",
      "description": "Write comments for the selected code"
    },
    {
      "name": "share",
      "description": "Export the current chat session to markdown"
    },
    {
      "name": "commit",
      "description": "Generate a git commit message"
    },
    {
      "name": "cmd",
      "description": "Generate a shell command"
    }
  ],
  "embeddingsProvider": {
    "model": "jina-bert-v2",
    "contextLength": 32768,
    "apiBase": "http://192.168.0.81:5003/v1/",
    "provider": "openai",
    "apiKey": "qwe"
  },
  "reranker": {
    "name": "free-trial"
  },
  "docs": [
    {
      "startUrl": "https://docs.djangoproject.com",
      "title": "Django",
      "faviconUrl": ""
    }
  ]
}

Description

With the recent update to "Continue version: 0.0.83" continue can't index docs anymore, this is logs:
[2024-12-15T13:32:58] Creating embeddings for 199 articles [2024-12-15T13:33:03] Creating embeddings for 199 articles [2024-12-15T13:33:23] Creating embeddings for 199 articles [2024-12-15T13:37:04] Adding 12862 embeddings to db [2024-12-15T13:37:14] Failed to fetch favicon for https://docs.djangoproject.com: TypeError: fetch failed [2024-12-15T13:37:14] Failed to find favicon for https://docs.djangoproject.com [2024-12-15T13:37:15] Adding 12862 embeddings to db [2024-12-15T13:37:25] Failed to fetch favicon for https://docs.djangoproject.com: TypeError: fetch failed [2024-12-15T13:37:25] Failed to find favicon for https://docs.djangoproject.com [2024-12-15T13:37:27] Error indexing docs Error: SQLITE_CONSTRAINT: UNIQUE constraint failed: docs.startUrl [2024-12-15T13:37:41] Adding 12862 embeddings to db [2024-12-15T13:37:51] Failed to fetch favicon for https://docs.djangoproject.com: TypeError: fetch failed [2024-12-15T13:37:51] Failed to find favicon for https://docs.djangoproject.com [2024-12-15T13:37:52] Error indexing docs Error: SQLITE_CONSTRAINT: UNIQUE constraint failed: docs.startUrl
happens all the time, several times tried to delete ~/.continue/index folder and restarting IDE - no success. In the embeddings model logs i see it creates many embedding, but seems to fail to write them to sqlite db.

To reproduce

No response

Log output

No response

@dosubot dosubot bot added area:indexing Relates to embedding and indexing kind:bug Indicates an unexpected problem or unintended behavior labels Dec 15, 2024
@RomneyDa
Copy link
Collaborator

@drrros thanks for the report. Is it happening with any besides https://docs.djangoproject.com?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
area:indexing Relates to embedding and indexing kind:bug Indicates an unexpected problem or unintended behavior "needs-triage"
Projects
None yet
Development

No branches or pull requests

2 participants