llmware-ai / llmware-ai/llmware

"Error binding parameter 22: type 'list' is not supported" when adding website using sqlite engine

Open
#1,042 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
14.8k
Forks
2.9k
PR merge metrics
No merged PRs in 30d

Description

  • Python 3.12
  • Windows 11 x64

My requirements.txt:

streamlit==1.39.0
llmware==0.3.7
# Progress bar
ipywidgets==8.1.5
# Web scraping
beautifulsoup4==4.12.3
lxml==5.3.0

My sample code:

from llmware.configs import LLMWareConfig
from llmware.models import ModelCatalog
from llmware.library import Library

# Set engine to save library data
LLMWareConfig().set_active_db('sqlite')

lib = Library().create_new_library(
    account_name = 'dhika',
    library_name = 'test_lib'
)

urls = [
    'https://en.tempo.co/read/1915490/prabowo-indifferent-to-gibrans-alleged-fufufafa-account-says-dasco',
    # More URLs after that
]

print(len(urls))

for url in urls:
    lib.add_website(
        url = url,
        # Don't search site recursively
        get_links = False
    )

Error result:

image

image

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the sample with Python 3.12, llmware 0.3.7, and the SQLite engine, focusing on the lib.add_website entry point and the reported parameter-binding error. Trace which value becomes the unsupported list and confirm that adding the supplied website succeeds without the SQLite error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, sqlite
Domain
databases
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.