Creating RAG from Scratch . Creating RAG using the langchain. Creating RAG using llama indexing and Qdrant db
-
Updated
Jun 13, 2024 - Jupyter Notebook
#
bert-score
Here are 15 public repositories matching this topic...
End-to-end MLOps pipeline that catches LLM quality regressions before production. Every PR is scored against a versioned golden dataset using BERTScore + ROUGE-L + an LLM-as-Judge rubric, compared to the MLflow production baseline, and shadowed against 5% of live traffic. FastAPI + Celery + TimescaleDB + Streamlit + DVC + GitHub Actions.
python docker redis celery openai regression-testing mlops roberta mlflow quality-gate drift-detection github-actions pydantic fastapi streamlit llm llmops llm-evaluation bert-score rouge-score
-
Updated
Jun 15, 2026 - Python
Evaluation metrics for ranking and retrieval
-
Updated
Apr 14, 2026 - Go
This repository contains Machine-Translation model for French and English languages
tokenizer machine-translation word-embeddings text-translation english-language encoder-decoder-model french-translation bert-model transformer-model bert-score
-
Updated
Jun 13, 2025 - Jupyter Notebook
Leveraging the BLIP Model for Visual Question Answering: A Comparative Analysis on VQA and DAQUAR Datasets
machine-learning natural-language-processing computer-vision inference accuracy image-captioning bleu-score blip visual-question-answering wups vqav2 bert-score daquar
-
Updated
Jun 18, 2024 - Jupyter Notebook
A RAG-based culinary QA system built with custom chunking, vectorisation, retrieval, and generation components.
-
Updated
Apr 23, 2026 - Jupyter Notebook
Multi-modal Summarization App using Streamlit, Whisper, and Transformers for audio/text input with model comparison and evaluation.
-
Updated
Jul 10, 2025 - Python
Different approaches to evaluate RAG !!!
-
Updated
Aug 13, 2024 - Jupyter Notebook
Explores text summarization using multiple approaches.
python nlp text-generation fine-tuning encoder-decoder-model perplexity state-of-the-art-models google-t5 large-language-models llm prompt-engineering mistral-7b bert-score
-
Updated
Feb 6, 2025 - Jupyter Notebook
Scientific text summarisation using LED, QLoRA fine-tuning, and HSSM evaluation on arXiv papers.
nlp machine-learning transformers pytorch led text-summarization rouge huggingface scientific-summarization generative-ai qlora bert-score
-
Updated
Jun 6, 2026 - Python
hybrid LLM-based automated test for AI generative models used by QA
-
Updated
Sep 10, 2025 - Python
📰 End-to-end NLP pipeline for news intelligence — fine-tuned RoBERTa multilabel classifier, spaCy NER, T5/BART entity-aware summarization & 5-signal misinformation risk scoring. Served via Streamlit. 🧠📊🚀
python numpy transformers pandas pytorch spacy joblib langdetect shap streamlit bert-score rouge-score scikit-learn-
-
Updated
Jun 15, 2026 - Python
Automated red-teaming framework for LLMs. Tests GPT-4o, Claude, Llama against OWASP Top 10 for LLMs using Red/Blue/Judge multi-agent architecture. Found 6 CRITICAL vulnerabilities in GPT-4o-mini in <3 min.
python owasp llama ai-safety security-testing red-teaming gpt4 prompt-injection llm-security bert-score
-
Updated
Mar 15, 2026 - Python
A tool for evaluating LLM responses against a knowledge base of expert solutions.
-
Updated
Aug 27, 2025 - Python
Comparative evaluation of neural machine translation architectures (MarianMT, mBART-50, NLLB-200, GPT-2) across German, Spanish, and Arabic. Includes multi-metric scoring (BLEU, chrF, METEOR, BERTScore, LaBSE), cross-lingual semantic similarity analysis, LLM-as-judge evaluation via LangChain, and WMT14/OPUS-100 benchmark runs.
multilingual python nlp machine-translation transformers semantic-analysis cross-lingual bleu huggingface mbart multilingual-nlp labse langchain sentance-transformers bert-score marionmt
-
Updated
Jun 19, 2026 - Python
Improve this page
Add a description, image, and links to the bert-score topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the bert-score topic, visit your repo's landing page and select "manage topics."