information-retrieval
elastic_transformers
information-retrieval | elastic_transformers | |
---|---|---|
3 | - | |
147 | 159 | |
- | - | |
0.0 | 0.0 | |
9 months ago | over 3 years ago | |
Jupyter Notebook | Jupyter Notebook | |
- | Apache License 2.0 |
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.
information-retrieval
-
[D] Generative vs embedding models
You can check out my repo https://github.com/kuutsav/information-retrieval. Here I've implemented some of the common embedding techniques from sbert from scratch.
-
Bi-Encoder with BERT does not learn
I have a bunch of training scripts here that night help you figure out the bug(if any) https://github.com/kuutsav/information-retrieval
-
[P] Created tutorials on Information Retrieval, specifically Semantic Search
Hi, I've created a repo which tries to cover the current progress in the world of information-retrieval using neural information retrievers / semantic search. Repo: https://github.com/kuutsav/information retrieval .
elastic_transformers
We haven't tracked posts mentioning elastic_transformers yet.
Tracking mentions began in Dec 2020.
What are some alternatives?
cherche - Neural Search
Multi-Type-TD-TSR - Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:
ttds-cw3-research-team - A Search Engine To Find Research Papers & Datasets
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
100DaysOfML - 100 Days Of Machine Learning. New Content in every 1-2 day and projects every week. The massive 100DaysOfML in building
Advertisement-Recommendation - Video Content-Based Advertisement Recommendation Using Text Classification
search-engine - Full stack search-engine created from youtube videos obtained using "web-scraping"
ocrpy - OCR, Archive, Index and Search: Implementation agnostic OCR framework.
CodeSearchNet - Datasets, tools, and benchmarks for representation learning of code.