mirror of
https://github.com/meilisearch/MeiliSearch
synced 2024-11-29 16:24:26 +01:00
chore: Rename the library "pentium" 🎉
This commit is contained in:
parent
13cf084751
commit
cf41b20fbb
@ -1,6 +1,6 @@
|
|||||||
[package]
|
[package]
|
||||||
edition = "2018"
|
edition = "2018"
|
||||||
name = "raptor"
|
name = "pentium"
|
||||||
version = "0.1.0"
|
version = "0.1.0"
|
||||||
authors = ["Kerollmops <renault.cle@gmail.com>"]
|
authors = ["Kerollmops <renault.cle@gmail.com>"]
|
||||||
|
|
||||||
|
24
README.md
24
README.md
@ -1,27 +1,31 @@
|
|||||||
# raptor-rs
|
# pentium
|
||||||
Raptor, the new RISE
|
|
||||||
|
A search engine based on the [blog posts serie](https://blog.algolia.com/inside-the-algolia-engine-part-1-indexing-vs-search/) of the great Algolia company.
|
||||||
|
|
||||||
|
This is a library, this means that binary are not part of this repository
|
||||||
|
but since I'm still nice I have made some examples for you in the `examples/` folder.
|
||||||
|
|
||||||
## Usage
|
## Usage
|
||||||
|
|
||||||
First you need to generate the index files.
|
Pentium work with an index like most of the search engines.
|
||||||
|
So to test the library you can create one by indexing a simple csv file.
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
$ cargo build --release
|
cargo build --release --example csv-indexer
|
||||||
$ time ./target/release/raptor-cli index csv --stop-words stop-words.txt the-csv-file.csv
|
time ./target/release/examples/csv-indexer --stop-words misc/en.stopwords.txt misc/kaggle.csv
|
||||||
```
|
```
|
||||||
|
|
||||||
The `stop-words.txt` file here is a simple file that contains one stop word by line.
|
The `en.stopwords.txt` file here is a simple file that contains one stop word by line (e.g. or, and...).
|
||||||
|
|
||||||
Once the command finished indexing you will have 3 files that compose the index:
|
Once the command finished indexing you will have 3 files that compose the index:
|
||||||
- The `xxx.map` represent the fst map.
|
- The `xxx.map` represent the fst map.
|
||||||
- The `xxx.idx` represent the doc indexes matching the words in the map.
|
- The `xxx.idx` represent the doc indexes matching the words in the map.
|
||||||
- The `xxx.sst` is a file that contains all the fields and the values asociated with it, it is passed to the internal RocksDB.
|
- The `xxx.sst` is a file that contains all the fields and the values asociated with it, it is passed to the internal RocksDB.
|
||||||
|
|
||||||
Now you can easily use `raptor server console` or `raptor serve http` with the name of the dump. (e.g. relaxed-colden).
|
Now you can easily run the `serve-console` or `serve-http` examples with the name of the dump. (e.g. relaxed-colden).
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
$ cargo build --release --default-features --features serve-console
|
cargo build --release --example serve-console
|
||||||
$ ./target/release/raptor-cli serve console --stop-words stop-words.txt relaxed-colden
|
./target/release/examples/serve-console relaxed-colden
|
||||||
```
|
```
|
||||||
|
|
||||||
Note: If you have performance issues run the searcher in release mode (i.e. `--release`).
|
|
||||||
|
@ -6,7 +6,7 @@ use std::fs::File;
|
|||||||
use std::io;
|
use std::io;
|
||||||
|
|
||||||
use csv::ReaderBuilder;
|
use csv::ReaderBuilder;
|
||||||
use raptor::{MetadataBuilder, DocIndex, Tokenizer, CommonWords};
|
use pentium::{MetadataBuilder, DocIndex, Tokenizer, CommonWords};
|
||||||
use rocksdb::{SstFileWriter, EnvOptions, ColumnFamilyOptions};
|
use rocksdb::{SstFileWriter, EnvOptions, ColumnFamilyOptions};
|
||||||
use structopt::StructOpt;
|
use structopt::StructOpt;
|
||||||
|
|
||||||
|
@ -7,7 +7,7 @@ use std::path::PathBuf;
|
|||||||
|
|
||||||
use serde_json::from_str;
|
use serde_json::from_str;
|
||||||
use rocksdb::{SstFileWriter, EnvOptions, ColumnFamilyOptions};
|
use rocksdb::{SstFileWriter, EnvOptions, ColumnFamilyOptions};
|
||||||
use raptor::{MetadataBuilder, DocIndex, Tokenizer, CommonWords};
|
use pentium::{MetadataBuilder, DocIndex, Tokenizer, CommonWords};
|
||||||
use structopt::StructOpt;
|
use structopt::StructOpt;
|
||||||
|
|
||||||
#[derive(Debug, StructOpt)]
|
#[derive(Debug, StructOpt)]
|
||||||
|
@ -5,8 +5,8 @@ use std::path::PathBuf;
|
|||||||
|
|
||||||
use elapsed::measure_time;
|
use elapsed::measure_time;
|
||||||
use rocksdb::{DB, DBOptions, IngestExternalFileOptions};
|
use rocksdb::{DB, DBOptions, IngestExternalFileOptions};
|
||||||
use raptor::rank::{criterion, Config, RankedStream, Document};
|
use pentium::rank::{criterion, Config, RankedStream};
|
||||||
use raptor::{automaton, DocumentId, Metadata, CommonWords};
|
use pentium::{automaton, DocumentId, Metadata};
|
||||||
|
|
||||||
#[derive(Debug, StructOpt)]
|
#[derive(Debug, StructOpt)]
|
||||||
pub struct CommandConsole {
|
pub struct CommandConsole {
|
||||||
|
@ -7,8 +7,8 @@ use std::path::PathBuf;
|
|||||||
use std::error::Error;
|
use std::error::Error;
|
||||||
use std::sync::Arc;
|
use std::sync::Arc;
|
||||||
|
|
||||||
use raptor::rank::{criterion, Config, RankedStream};
|
use pentium::rank::{criterion, Config, RankedStream};
|
||||||
use raptor::{automaton, Metadata, CommonWords};
|
use pentium::{automaton, Metadata};
|
||||||
use rocksdb::{DB, DBOptions, IngestExternalFileOptions};
|
use rocksdb::{DB, DBOptions, IngestExternalFileOptions};
|
||||||
use warp::Filter;
|
use warp::Filter;
|
||||||
use structopt::StructOpt;
|
use structopt::StructOpt;
|
||||||
|
Loading…
Reference in New Issue
Block a user