wish-knowledge-loader
A CLI tool for managing knowledge bases in wish.
Overview
wish-knowledge-loader is a command-line tool that allows you to:
- Load knowledge from GitHub repositories into wish
- List existing knowledge bases
- Delete knowledge bases when no longer needed
For detailed usage instructions, see the Knowledge Loader Usage Guide.
Installation
# Install from the repository
cd wish-knowledge-loader
uv sync --dev
cp .env.example .env
vim .env # Set the OpenAI API key
Quick Reference
# Load a knowledge base
wish-knowledge-loader load --repo-url https://github.com/username/repo --glob "**/*.md" --title "Knowledge Base Title"
# List all knowledge bases
wish-knowledge-loader list
# Delete a knowledge base
wish-knowledge-loader delete --title "Knowledge Base Title"
Environment Variables
The following environment variables can be set in a .env file:
OPENAI_API_KEY: Your OpenAI API key (required)OPENAI_EMBEDDING_MODEL: OpenAI embedding model to use (default: "text-embedding-3-small")WISH_HOME: Path to the wish home directory (default: "~/.wish")
Development
# Run tests
uv run pytest
# Run linting
uv run ruff check .
Verifying Search Functionality
After creating a knowledge base, you can verify the search functionality using the provided script:
# Set the OpenAI API key
export OPENAI_API_KEY="your-api-key"
# Run the search script
python scripts/search_knowledge.py "Knowledge Base Title" "your search query"
The script will:
- Load the vector store for the specified knowledge base
- Search for documents similar to your query
- Display the top 4 results with their content and metadata
You can adjust the number of results by modifying the k parameter in the script.
Metadata
Release files for wish-knowledge-loader 0.6.28
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| wish_knowledge_loader-0.6.28.tar.gz | 36.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| wish_knowledge_loader-0.6.28-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 70.5 kB
Release files / wish_knowledge_loader-0.6.28.tar.gz
| Download URL | wish_knowledge_loader-0.6.28.tar.gz |
|---|---|
| Size | 36.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4c230bbae0dc4544c04896721d7e0cc205f594261ce8e6d6bbdc8e50e2fe5229
|
|
BLAKE2b-256 checksum How to use checksums |
0e72d55239b2eeb21315c62229bd0dd4b45f6b90b00da77bd9a9d52c0c83e57a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|
Release files / wish_knowledge_loader-0.6.28-py3-none-any.whl
| Download URL | wish_knowledge_loader-0.6.28-py3-none-any.whl |
|---|---|
| Size | 34.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
542a79526d3b693868fd2bedf57903dc9d7b20bd98f0d7e9814f7b1e3bdd8ede
|
|
BLAKE2b-256 checksum How to use checksums |
3aab0508011477824d835452f960c85ea13c981a1fbf8b7b27e60a245d80b073
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.3
|