CodeSoul-co/THETA
LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining
This platform helps social scientists analyze large collections of text documents to uncover underlying themes and trends. You input raw text files like articles, reports, or social media data, and it outputs detailed topic lists, word clouds, network visualizations, and comprehensive metrics about the discovered topics. Researchers in fields like sociology, political science, and communication studies would use this to systematically understand their qualitative data.
Use this if you need to perform advanced topic modeling on large social science text datasets to extract meaningful insights and understand the core discussions within them.
Not ideal if your primary goal is simple keyword extraction or if you are working with non-textual data.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/CodeSoul-co/THETA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ContextualAI/gritlm
Generative Representational Instruction Tuning
xlang-ai/instructor-embedding
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
liuqidong07/LLMEmb
[AAAI'25 Oral] The official implementation code of LLMEmb
hpcaitech/CachedEmbedding
A memory efficient DLRM training solution using ColossalAI
ritesh-modi/embedding-hallucinations
This repo shows how foundational model hallucinates and how we can fix such hallucinations using...