| Crates.io | semantic-search-cli |
| lib.rs | semantic-search-cli |
| version | 0.1.7 |
| created_at | 2025-03-09 01:07:23.193607+00 |
| updated_at | 2025-07-14 01:23:29.733673+00 |
| description | 🔎 Semantic search cli. |
| homepage | |
| repository | https://github.com/PRO-2684/Semantic-Search |
| max_upload_size | |
| id | 1584989 |
| size | 150,147 |
🔎 Semantic search cli.
There are two ways to install the CLI:
cargo install semantic-search-clicargo binstall semantic-search-cliThe configuration file is located at .sense/config.toml. You should create this file if it does not exist.
[api]
key = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # API key for SiliconCloud (Required)
model = "BAAI/bge-large-zh-v1.5" # Model to use for embedding (Optional)
endpoint = "https://api.siliconflow.cn" # API endpoint (Optional)
# Alternative: https://api.siliconflow.com
[bot] # Only required for `sense bot`
token = "1234567890:xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" # Telegram bot token (Required)
owner = 1234567890 # Telegram user ID of the bot owner (Required)
whitelist = [] # Whitelisted user IDs (Optional)
sticker_set = "meme" # Sticker set id prefix for the bot (Optional, an additional `_by_<bot_username>` will be appended to form the full sticker set id)
num_results = 8 # Number of results to return (Optional)
postscript = "" # Postscript to be appended after the help message (Optional)
[server]
port = 8080 # Default port for the server (Optional)
[api] section)api.key: Required. API key for SiliconCloud. You can get one from SiliconCloud for free.api.model: Optional. Model to use for embedding. Available models:
[bot] section)This section is only required if you want to deploy the Telegram bot (sense bot).
bot.token: Required. Telegram bot token. You can get one from BotFather.bot.owner: Required. Telegram user ID of the bot owner. You can get your user ID from IDBot.bot.whitelist: Optional. Whitelisted user IDs. Only these users can use the bot. If not set or set to an empty array, all users can use the bot.bot.sticker_set: Optional. Sticker set id prefix for the bot. It must begin with a letter and can't contain consecutive underscores. An additional _by_<bot_username> will be appended to form the full sticker set id, as required by Telegram. Default is meme.bot.num_results: Optional. Number of results to return. Default is 8.bot.postscript: Optional. Postscript to be appended after the help message, formatted in HTML style. Default is an empty string.[server] section)TBD
(Re-)Index the files you want to search for by executing the following command:
sense index
This will generate or update index of the files, their hashes, labels and embeddings in .sense/index.db3. Note that each time you add or remove files, you need to re-run this process.
If files are created or changed, running this command will prompt you to label them (again). You can use any tool of your choice to label them automatically. See DEV.md for more information on the database schema.
To search for files based on labels, execute the following command:
sense search "cute cat"
You can specify how many results you want to display using the --num-results flag, or -n for short:
sense search "cute cat" -n 8 # Default
(TBD) Also, you can specify the regular expression for the path of the files using the --path flag, or -p for short:
sense search "cute cat" -p "path/.*\.jpg"
You can start a Telegram bot to search for files using a chat interface:
sense tg
See TELEGRAM.md for detailed instructions on deploying the bot.
You can start a server to search for files using a REST API:
sense serve --port 8080
Which will start a server on port 8080. You can then search for files using the following endpoint:
$ curl -X POST http://localhost:8080/search -d '{"query": "cute cat", "limit": 5, "ext": "jpg"}'
{"files":["cute-cat.jpg","cute-cat-2.jpg","cute-cat-3.jpg","cute-cat-4.jpg","cute-cat-5.jpg"]}
libssl.so.1.1: cannot open shared object file: No such file or directoryunwrap(), so as to make the program more robust to network failures@ in commands