Learn how to leverage PyAirbyte and use Postgres as a Cache, while running in a Google Colab only. It installs packages on the system and requires sudo access.
Learn how to use PyAirbyte to extract cryptocurrency data from CoinAPI.io, and load it to Snowflake, followed by a series of transformations and analyses to derive meaningful insights from this data.
Learn how to build a RAG pipeline, extracting data from a file source using PyAirbyte, storing it in a Pinecone vector store, and then using LangChain to perform RAG on the stored data.
Learn how to build a full data stack using Airbyte Cloud, Terraform, and dbt to move data from S3 -> BigQuery -> Pinecone for interacting with fetched data through an LLM and form a full fledged RAG.
Learn how to load data from GitHub airbyte-source into Snowflake using PyAirbyte, and afterwards convert the stream data into vector.
In a world where e-commerce business models are relatively uniform, lies a huge opportunity in analytics of building modular, reusable data transformation models. This tutorial is about open sourcing the full end to end pipeline around a critical use case for every e-commerce: profitability calculation!
Learn how to load user review data from Google Sheets intoS nowflake Cortex based vector store, and perform sentiment analysis using Snowflake Cortex's sentiment function.
Learn how to automate and monitor Airbyte Cloud sync jobs using PyAirbyte. It includes setting up job executions, handling dependencies, sending real-time status updates, and visually representing job details and outcomes on a timeline.
Learn how to use PyAirbyte to ingest cryptocurrency data from CoinAPI.io into Snowflake.
Learn how to set up a RAG pipeline from GitHub, using PyAirbyte, storing the data in Chroma, using LangChain to perform RAG on the stored data.
Learn how to build a simple RAG (Retrieval-Augmented Generation) pipeline with Milvus Lite and PyAirbyte, for a fully local development in Python.
Learn how to build a RAG pipeline, extracting data from Jira using PyAirbyte, storing it in a Pinecone vector store, and then using LangChain to perform RAG on the stored data.