Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.

Last update: Nov 29, 2022

Overview

Cherche

Neural search

Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers. Cherche is meant to be used with small to medium sized corpora. Cherche's main strength is its ability to build diverse and end-to-end pipelines.

Installation 🤖

pip install cherche

To install the development version:

pip install git+https://github.com/raphaelsty/cherche

Documentation 📜

Documentation is available here. It provides details about retrievers, rankers, pipelines, question answering, summarization, and examples.

QuickStart 💨

Documents 📑

Cherche allows findings the right document within a list of objects. Here is an example of a corpus.

from cherche import data

documents = data.load_towns()

documents[:3]
[{'id': 0,
  'title': 'Paris',
  'url': 'https://en.wikipedia.org/wiki/Paris',
  'article': 'Paris is the capital and most populous city of France.'},
 {'id': 1,
  'title': 'Paris',
  'url': 'https://en.wikipedia.org/wiki/Paris',
  'article': "Since the 17th century, Paris has been one of Europe's major centres of science, and arts."},
 {'id': 2,
  'title': 'Paris',
  'url': 'https://en.wikipedia.org/wiki/Paris',
  'article': 'The City of Paris is the centre and seat of government of the region and province of Île-de-France.'
  }]

Retriever ranker 🔍

Here is an example of a neural search pipeline composed of a TfIdf that quickly retrieves documents, followed by a ranking model. The ranking model sorts the documents produced by the retriever based on the semantic similarity between the query and the documents.

from cherche import data, retrieve, rank
from sentence_transformers import SentenceTransformer

# List of dicts
documents = data.load_towns()

# Retrieve on fields title and article
retriever = retrieve.TfIdf(key="id", on=["title", "article"], documents=documents, k=30)

# Rank on fields title and article
ranker = rank.Encoder(
    key = "id",
    on = ["title", "article"],
    encoder = SentenceTransformer("sentence-transformers/all-mpnet-base-v2").encode,
    k = 3,
    path = "encoder.pkl"
)

# Pipeline creation
search = retriever + ranker

search.add(documents=documents)

search("Bordeaux")
[{'id': 57, 'similarity': 0.69513476},
 {'id': 63, 'similarity': 0.6214991},
 {'id': 65, 'similarity': 0.61809057}]

Map the index to the documents to access their contents.

search += documents
search("Bordeaux")
[{'id': 57,
  'title': 'Bordeaux',
  'url': 'https://en.wikipedia.org/wiki/Bordeaux',
  'article': 'Bordeaux ( bor-DOH, French: [bɔʁdo] (listen); Gascon Occitan: Bordèu [buɾˈðɛw]) is a port city on the river Garonne in the Gironde department, Southwestern France.',
  'similarity': 0.69513476},
 {'id': 63,
  'title': 'Bordeaux',
  'url': 'https://en.wikipedia.org/wiki/Bordeaux',
  'article': 'The term "Bordelais" may also refer to the city and its surrounding region.',
  'similarity': 0.6214991},
 {'id': 65,
  'title': 'Bordeaux',
  'url': 'https://en.wikipedia.org/wiki/Bordeaux',
  'article': "Bordeaux is a world capital of wine, with its castles and vineyards of the Bordeaux region that stand on the hillsides of the Gironde and is home to the world's main wine fair, Vinexpo.",
  'similarity': 0.61809057}]

Retrieve 👻

Cherche provides different retrievers that filter input documents based on a query.

retrieve.Elastic
retrieve.TfIdf
retrieve.Lunr
retrieve.BM25Okapi
retrieve.BM25L
retrieve.Flash
retrieve.Encoder

Rank 🤗

Cherche rankers are compatible with SentenceTransformers models, Hugging Face sentence similarity models, Hugging Face zero shot classification models, and of course with your own models.

Summarization and question answering

Cherche provides modules dedicated to summarization and question answering. These modules are compatible with Hugging Face's pre-trained models and can be fully integrated into neural search pipelines.

Acknowledgements 👏

The BM25 models available in Cherche are wrappers around rank_bm25. Elastic retriever is a wrapper around Python Elasticsearch Client. TfIdf retriever is a wrapper around scikit-learn's TfidfVectorizer. Lunr retriever is a wrapper around Lunr.py. Flash retriever is a wrapper around FlashText. DPR and Encode rankers are wrappers dedicated to the use of the pre-trained models of SentenceTransformers in a neural search pipeline. ZeroShot ranker is a wrapper dedicated to the use of the zero-shot sequence classifiers of Hugging Face in a neural search pipeline.

Dev Team 💾

The Cherche dev team is made up of Raphaël Sourty and François-Paul Servant 🥳

Comments

Added spelling corrector object

Hello ! I added a spelling corrector base class as well as the original implementation of the Norvig spelling corrector. The spelling corrector can be fitted directly on the pipeline's documents with the '.add(documents)' method. I also provided an optional (defaults to False) external dictionary, the one originally used by Norvig.

I have no issue updating my code for improvements, so feel free to suggest any modification !

opened by NicolasBizzozzero 4
0.0.5
Pull request for Cherche version 0.0.5

RAG: add RAG generator for open domain question answering

RapidFuzzy: New blazzing fast retriever

Retrievers: Provide similarities for each retriever

Union & Intersection: Keep similarity scores
opened by raphaelsty 1
Batch processing
Retrieving documents with batch of queries can significantly speed up things. It is now available for few models using the development version via the batch method.

Models involved are:

TfIdf retriever

Encoder retriever (milvus + faiss)

Encoder ranker (milvus)

DPR retriever (milvus + faiss)

DPR ranker (milvus)

Recommend retriever

Batch is not yet compatible with pipelines.
enhancement
opened by raphaelsty 0
Cherche 1.0.0
Here is an essential update for Cherche. The update retains the previous API and is compatible with previous versions. 🥳

Main additions:

Added compatibility with two new open-source retrievers: Meilisearch and TypeSense.

Compatibility with the Milvus index to use the retriever.Encoder and retriever.DPR models on massive corpora.

Compatibility with the Milvus index to store ranker embeddings in a database rather than in memory.

Progress bar when pre-computing embeddings by Encoder, DPR retrievers and Encoder, DPR rankers.

All pipelines (voting, intersection, concatenation) produce a similarity score. To do so, the pipeline object applies a softmax to normalize the scores, thus allowing us to "compare" the scores of two distinct models.

Integration of collaborative filtering models via adding a Recommend retriever and a Recommend ranker (indexation via Faiss and compatible with Milvus) to consider users' preferences in the search.
opened by raphaelsty 0
"IndexError: index out of range in self "While adding documents to cherche pipeline

I'm using a cherche pipline built of a tfidf retriever with a sentencetransformer ranker as follows : search = (retriever + ranker) While trying to add documents to the pipeline (search.add(documents=documents), I got this error :

"""/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse) 2181 # remove once script supports set_grad_enabled 2182 no_grad_embedding_renorm(weight, input, max_norm, norm_type) -> 2183 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) 2184 2185

IndexError: index out of range in self"""

opened by delmetni 0
incomplete doc about metrics

https://raphaelsty.github.io/cherche/examples/eval_pipeline/ you say that one can find the explnaation about metrics here https://amitness.com/2020/08/information-retrieval-evaluation/ but it doesn't say what "precision" and "r-precision" are.

opened by fpservant 0

Releases(1.0.1)

1.0.1(Oct 27, 2022)

Removed the dependency with grpcio that can cause problems during installation.
Source code(tar.gz)
Source code(zip)
1.0.0(Oct 26, 2022)
What's Changed

Here is an essential update for Cherche! 🥳

Added compatibility with two new open-source retrievers: Meilisearch and TypeSense.

Compatibility with the Milvus index to use the retriever.Encoder and retriever.DPR models on massive corpora.

Compatibility with the Milvus index to store ranker embeddings in a database rather than in memory.

Progress bar when pre-computing embeddings by Encoder, DPR retrievers and Encoder, DPR rankers.

The path parameter is no longer used.

All pipelines (voting, intersection, concatenation) produce a similarity score. To do so, the pipeline object applies a softmax to normalize the scores, thus allowing us to "compare" the scores of two distinct models.

Integration of collaborative filtering models via adding a Recommend retriever and a Recommend ranker (indexation via Faiss and compatible with Milvus) to consider users' preferences in the search.

Cherche is now fully compatible with large-scale corpora and deeply integrates collaborative filtering. Updates retains the previous API and is compatible with previous versions.
Source code(tar.gz)
Source code(zip)
0.1.0(Jun 16, 2022)

Added compatibility with the ONNX environment and quantization to significantly speed up sentence transformers and question answering models. 🏎

It is now possible to choose the type of index for the Encoder and DPR retrievers in order to process the largest corpora while using the GPU.
Source code(tar.gz)
Source code(zip)
0.0.9(Apr 13, 2022)

Voting operator dedicated to retrievers and rankers.
Source code(tar.gz)
Source code(zip)
0.0.8(Mar 7, 2022)

Avoid checking similarities in TF-IDF retrievers while filtering documents.
Source code(tar.gz)
Source code(zip)
0.0.7(Mar 7, 2022)
Significant improvement in the speed of the TF-IDF retriever using sparse CSC matrix.

The setup.py file loads the readme file as UTF-8.

Source code(tar.gz)
Source code(zip)
0.0.6(Mar 3, 2022)
Update documentation

Update retriever Encoder and DPR, path is optionnal

Add deployment documentation

Update similarity type

Avoid round similarity

Source code(tar.gz)
Source code(zip)
0.0.5(Feb 8, 2022)
Loading and Saving tutorial

Fuzzy retriever

Similarities everywhere (retrievers, union, intersection provide similarity scores)

RAG generation

Source code(tar.gz)
Source code(zip)
0.0.4(Jan 20, 2022)

Update of the encoder retriever and the DPR retriever. Documents in the Faiss index will not be duplicated. Query embeddings can now be pre-computed for ranker Encoder and ranker DPR to speed up evaluation without having to compute it again.
Source code(tar.gz)
Source code(zip)
0.0.3(Jan 13, 2022)
Adding:

Translation

DPR retriever

Source code(tar.gz)
Source code(zip)
0.0.2(Jan 12, 2022)

Update of the Cherche dependencies. The previous dependencies were too strict and restrictive as they were limited to a specific version for each package.
Source code(tar.gz)
Source code(zip)
0.0.1(Jan 8, 2022)

Source code(tar.gz)
Source code(zip)

Owner

Raphael Sourty

PhD Student @ IRIT and Renault

GitHub Repository

ADCS - Automatic Defect Classification System (ADCS) for SSMC

Table of Contents Table of Contents ADCS Overview Summary Operator's Guide Demo System Design System Logic Training Mode Production System Flow Folder

2 Jun 24, 2022

An assignment from my grad-level data mining course demonstrating some experience with NLP/neural networks/Pytorch

NLP-Pytorch-Assignment An assignment from my grad-level data mining course (before I started personal projects) demonstrating some experience with NLP

0 Feb 06, 2022

a CTF web challenge about making screenshots

screenshotter (web) A CTF web challenge about making screenshots. It is inspired by a bug found in real life. The challenge was created by @LiveOverfl

219 Jan 02, 2023

This is Assignment1 code for the Web Data Processing System.

This is a Python program to Entity Linking by processing WARC files. We recognize entities from web pages and link them to a Knowledge Base(Wikidata).

3 Dec 04, 2022

Simple, hackable offline speech to text - using the VOSK-API.

844 Jan 07, 2023

Fake Shakespearean Text Generator

Fake Shakespearean Text Generator This project contains an impelementation of stateful Char-RNN model to generate fake shakespearean texts. Files and

1 Feb 15, 2022

TFPNER: Exploration on the Named Entity Recognition of Token Fused with Part-of-Speech

TFPNER TFPNER: Exploration on the Named Entity Recognition of Token Fused with Part-of-Speech Named entity recognition (NER), which aims at identifyin

1 Feb 07, 2022

Named Entity Recognition API used by TEI Publisher

TEI Publisher Named Entity Recognition API This repository contains the API used by TEI Publisher's web-annotation editor to detect entities in the in

14 Nov 15, 2022

InferSent sentence embeddings

InferSent InferSent is a sentence embeddings method that provides semantic representations for English sentences. It is trained on natural language in

2.2k Dec 27, 2022

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

In recent years, the dense retrievers based on pre-trained language models have achieved remarkable progress. To facilitate more developers using cutt

475 Jan 04, 2023

Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.

Related tags

Overview

Cherche

Installation 🤖

Documentation 📜

QuickStart 💨

Documents 📑

Retriever ranker 🔍

Retrieve 👻

Rank 🤗

Summarization and question answering

Acknowledgements 👏

See also 👀

Dev Team 💾

Comments

Added spelling corrector object

0.0.5

Batch processing

Cherche 1.0.0

"IndexError: index out of range in self "While adding documents to cherche pipeline

incomplete doc about metrics

Releases(1.0.1)

1.0.1(Oct 27, 2022)

1.0.0(Oct 26, 2022)

What's Changed

Here is an essential update for Cherche! 🥳

0.1.0(Jun 16, 2022)

0.0.9(Apr 13, 2022)

0.0.8(Mar 7, 2022)

0.0.7(Mar 7, 2022)

0.0.6(Mar 3, 2022)

0.0.5(Feb 8, 2022)

0.0.4(Jan 20, 2022)

0.0.3(Jan 13, 2022)

0.0.2(Jan 12, 2022)

0.0.1(Jan 8, 2022)

Owner

Raphael Sourty

ADCS - Automatic Defect Classification System (ADCS) for SSMC

An assignment from my grad-level data mining course demonstrating some experience with NLP/neural networks/Pytorch

a CTF web challenge about making screenshots

This is Assignment1 code for the Web Data Processing System.

Simple, hackable offline speech to text - using the VOSK-API.

Fake Shakespearean Text Generator

TFPNER: Exploration on the Named Entity Recognition of Token Fused with Part-of-Speech

Named Entity Recognition API used by TEI Publisher

InferSent sentence embeddings

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

Automatic privilege escalation for misconfigured capabilities, sudo and suid binaries

Model parallel transformers in JAX and Haiku

nlp基础任务

Code voor mijn Master project omtrent VideoBERT

PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"

To classify the News into Real/Fake using Features from the Text Content of the article

A NLP program: tokenize method, PoS Tagging with deep learning

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

Chinese segmentation library

REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.