Prashanth Rao's repositories
fine-grained-sentiment
A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.
llama_index
LlamaIndex is a data framework for your LLM applications
kuzudb-study
Benchmark study on KùzuDB, an embedded OLAP graph database, on an artificial social network dataset
awesome-duckdb
🦆 A curated list of awesome DuckDB resources
spacy-nlp
Natural Language Processing experiments using the spaCy library
topic-modelling
Comparing the scalability and quality of topic models in Gensim and PySpark
kuzu-rdflib
An integration of KùzuDB and RDFlib.
pydantic-benchmarks
Benchmarks testing the performance of various releases of Pydantic v2 🦀
AeonG
AeonG: An Efficient Built-in Temporal Support in Graph Databases
rustworkx
A high performance Python graph library implemented in Rust.
this-week-in-rust
Data for this-week-in-rust.org
lancedb-study
Benchmark study on LanceDB, an embedded vector DB, for full-text search and vector search
lancedb
Serverless, low-latency vector database for AI applications
prrao87.github.io
Archived. My blog is now moved to https://github.com/thedataquarry
db-hub-fastapi
Async bulk data ingestion and querying in various document, graph and vector databases via their Python clients
mteb-validation
Compare different embedding models from MTEB leaderboard
meilisearch-python-sdk
An async and sync Python client for the Meilisearch API
rag-data-ops
Code for data ops when building RAG applications using LangChain and LlamaIndex
kuzu-ui
Browser-based user interface for Kùzu graph database
VectorHub
VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.
duckdb-study
Compare DuckDB, Polars and Pandas for generating an artificial dataset of persons and companies
weaviate-io
Website for the Weaviate vector database
qdrant-client
Python client for Qdrant vector search engine
gh-action-test
Test GitHub actions and pre-commit hooks for experimenting with CI/CD and auto-linting workflows.
neo4j-python-fastapi
Bulk ingest data into Neo4j using sync or async Python, and expose the data via FastAPI
fine-grained-sentiment-app
A Flask LIME explainer app for fine-grained sentiment classification.
spacy-experimental-coref
Testing the new coreference resolver in spaCy v3.x