NLP and Text

Combine BM25 keyword search with Qwen3-Embedding-8B dense vectors in Qdrant to build a retrieval pipeline that beats either approach alone—with working Python code.

Resolve pronouns and noun phrases to their referents using spaCy coreferee and transformer-based models for cleaner NLP output.

Find the best chunking strategy for your RAG pipeline by benchmarking four methods side by side.

Combine BM25 and vector search with Reciprocal Rank Fusion to get better results than either approach alone.

Extract grammatically correct keyphrases from documents using POS-pattern vectorizers instead of fixed n-gram windows

Detect any language and translate it to English or other targets using lingua and MarianMT in a single FastAPI service.

Extract legal entities like case citations, statutes, and parties from text using Transformers and spaCy

Analyze sentiment in any language with a single model using XLM-RoBERTa and Hugging Face Transformers

Link named entities in text to Wikipedia articles using spaCy for NER and cross-encoder models for disambiguation

Extract relationships like works_at and founded_by from text using spaCy, transformers, and LLMs to build knowledge graphs.

Extract structured data from resumes using spaCy for entity recognition and Transformers for section classification.

Create search that understands both meaning and mood by combining sentence embeddings with sentiment analysis

Create a fast spell checker that handles typos, misspellings, and domain-specific terms with Python libraries.

Detect and anonymize names, emails, phone numbers, and custom PII patterns in text with Presidio

Pick the right chunking strategy for your RAG app and stop losing retrieval quality to bad splits

Build accurate text classifiers with minimal labeled data using SetFit’s few-shot learning approach

Cluster text documents into meaningful groups without labeled data using embeddings, UMAP, and HDBSCAN in Python

Create automated text correction systems using rule-based tools, neural models, and LLMs with practical Python examples and performance benchmarks.

Find and remove near-duplicate texts at scale using MinHash fingerprints and LSH for fast similarity search

Create a semantic search system that encodes text into vectors and finds similar documents in milliseconds using FAISS indices.

Classify whether text pairs agree, contradict, or are unrelated using NLI models and Transformers

Clean messy real-world text with a composable pipeline covering encoding fixes, Unicode normalization, spell correction, and more.

Generate high-quality paraphrases with T5 and PEGASUS, score them by similarity, and batch process text

Score any text with multiple readability indices and serve results through a FastAPI endpoint you can deploy today.

Ship a production-ready text similarity endpoint using cross-encoders that outperform cosine similarity

Rewrite text across styles — formal to casual, technical to simple, passive to active — with working Python pipelines.

Combine extractive summarization with Sumy and abstractive models from Transformers for a hybrid text summarization pipeline

Turn unstructured text into a knowledge graph you can query and visualize with SpaCy and NetworkX

Create a summarization pipeline that generates concise summaries from long documents with PEGASUS

Go beyond document-level sentiment and analyze what people think about specific aspects of products

Classify text into 27 emotion categories with fine-tuned Transformers and serve predictions via FastAPI

Extract precise answers from documents with transformer-based QA models that point to the exact text span

Build a text deduplication pipeline that scales to millions of documents using datasketch, sentence-transformers, and scikit-learn

Pull the most important terms from any text using embedding-based keyword extraction that actually understands context

Turn scanned documents into structured data with LayoutLM’s combined text, layout, and image understanding

Encode text in 50+ languages into a shared vector space for search, classification, and similarity scoring.

Extract named entities from any text using spaCy pretrained models, transformer-based NER, and zero-shot GLiNER.

Ground your LLM answers in real documents with a working RAG pipeline you can run locally

Create a search engine that understands meaning, not just keywords, using OpenAI embeddings

Ship a sentiment analysis endpoint in under 100 lines of Python using a fine-tuned RoBERTa model and FastAPI.

Build a pipeline that turns plain English questions into validated SQL queries you can run against any database.

Build a text classification pipeline with LLMs that handles any label set without training data or fine-tuning.

Build a pipeline that parses invoices and receipts from PDF to validated, typed JSON in under 50 lines of Python.

Build production-ready topic models that actually surface meaningful themes from your text data using BERTopic

Break long documents into chunks, summarize each one in parallel, and combine the results into a final summary.