lunr.py
cherche
| lunr.py | cherche | |
|---|---|---|
| 2 | 12 | |
| 196 | 326 | |
| 2.0% | -0.3% | |
| 4.4 | 6.2 | |
| about 2 months ago | 9 months ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lunr.py
-
[P] Library for end-to-end neural search pipelines
I started developing this tool after using haystack. Pipelines are easier to build with cherche because of the operators. Also, cherche offers FlashText, Lunr.py retrievers that are not available in Haystack and that I needed for the project I wanted to solve. Haystack is clearly more complete but I think also more complex to use.
-
Poor search results in Obsidian
I simply reused (**cough** stole **cough**) mkdoc's implementation. I used to be running a local version of mkdocs for this, but later just used lunr.py and a simple webpage including lunr.js and a search field.
cherche
-
[P] Semantic search
If you are interested, you can check out the documentation here: https://github.com/raphaelsty/cherche
- Minimalist semantic search with Cherche 2.0
-
[D] is it time to investigate retrieval language models?
Here is a tool I made to create retriever-reader pipeline in a minute: Cherche, would recommend also Haystack on github !
- [P] Cherche - allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.
- Cherche - allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.
- GitHub - raphaelsty/cherche: Neural search
-
[P] Library for end-to-end neural search pipelines
Github link Documentation Hackernews link
-
Hacker News top posts: Jan 10, 2022
Neural Search for medium sized corpora\ (3 comments)
-
Neural search library in Python for medium-sized corpora
https://github.com/raphaelsty/cherche
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.
- Neural Search for medium sized corpora
What are some alternatives?
flashtext - Extract Keywords from sentence or Replace keywords in sentences.
primeqa - The prime repository for state-of-the-art Multilingual Question Answering research and development.
faiss - A library for efficient similarity search and clustering of dense vectors.
mteb - MTEB: Massive Text Embedding Benchmark
mindflow - 🧠code-awareness
rank_bm25 - A Collection of BM25 Algorithms in Python
tableQA-Chinese - Unsupervised tableQA and databaseQA on chinese finance question and tabular data
weaviate-txtai - An integration of the weaviate vector search engine with txtai
gpl - Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577
oneline - Read a text file, one line at a time
NetShears - iOS Network monitor/interceptor framework