The langchain-airbyte package integrates LangChain with Airbyte. It has a very powerful function AirbyteLoader which can be used to load data as document into langchain from any Airbyte source.
Learn how to use PyAirbyte to load data from Facebook marketing, store the data in Milvus (Zilliz) vector store and perform a short RAG demo (using OpenAI/LangChain).
Learn how to load data from Github into Weaviate using PyAirbyte, then to use source-github and its stream 'issues'.
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 build an end-to-end RAG pipeline, extracting data from Google Drive using PyAirbyte, storing it in Pinecone, and then using LangChain to perform RAG on the stored data.
Learn how to use polygon.io as a data source and use the Langchain experimental agent.
Learn how to build an end-to-end RAG pipeline, extracting data from Gitlab using PyAirbyte, storing it in Qdrant, and then using LangChain to perform RAG on the stored data.
Learn how to build an end-to-end RAG pipeline, extracting data from Shopify using PyAirbyte, storing it on Pinecone, and then use LangChain to perform RAG on the stored data.
Learn how to scrape customer reviews from an Amazon product page, loading the data into Snowflake Cortex, and performing summarization.
Learn how to build an end-to-end RAG pipeline, extracting data from an S3 bucket using PyAirbyte, storing it in a Pinecone vector store, and then use LangChain to perform RAG on the stored data.
Learn how to scrape data from a website and load it in a database using PyAirbyte and LangChain. Integrating web data into LLMs can enhance their performance by providing up-to-date and relevant information.
Learn how to set up an end-to-end RAG pipeline using Airbyte Cloud, Amazon S3, and Snowflake Cortex.