cohere-ai / sandbox-topically
Topic modeling helpers using managed language models from Cohere. Name text clusters using large GPT models.
☆214Updated last year
Related projects: ⓘ
- Conversational AI tooling & personas built on Cohere's LLMs☆173Updated last year
- A sandbox repo for grounded question answering with Cohere and Google Search☆135Updated last year
- A demonstration of how a toy (but usable!) semantic search engine can be quickly built using Cohere's platform.☆113Updated last year
- ☆46Updated this week
- [EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.☆99Updated 4 months ago
- FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes☆180Updated last month
- This repository contains an easy and intuitive approach to use SetFit in combination with spaCy.☆71Updated last year
- ✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3☆318Updated last year
- 💫 SpaCy wrapper for ConceptNet 💫☆88Updated last year
- SpanMarker for Named Entity Recognition☆384Updated last month
- just a bunch of useful embeddings☆458Updated last week
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆99Updated 8 months ago
- Evaluation of language models on mono- or multilingual tasks.☆71Updated last month
- Generalist and Lightweight Model for Relation Extraction (Extract any relationship types from text)☆77Updated this week
- Augmenty is an augmentation library based on spaCy for augmenting texts.☆149Updated 3 months ago
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: …☆321Updated last year
- Clustering sentence embeddings to extract message intent☆166Updated 2 years ago
- Semantic search through a vectorized Wikipedia (SentenceBERT) with the Weaviate vector search engine☆241Updated last year
- A Python library aimed at dissecting and augmenting NER training data.☆56Updated last year
- This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with enti…☆240Updated last year
- ☆75Updated last year
- Late Interaction Models Training & Retrieval☆130Updated last week
- Pinecone text client library☆52Updated last month
- TimeLMs: Diachronic Language Models from Twitter☆100Updated 6 months ago
- Notebooks for training universal 0-shot classifiers on many different tasks☆100Updated 5 months ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆300Updated last year
- Information extraction from English and German texts based on predicate logic☆133Updated last year
- Explainable Zero-Shot Topic Extraction☆62Updated last month
- SKILLSPAN: Competences as Spans for Skill Extraction from Job Postings☆52Updated 7 months ago