Notebooks
E
Elastic
Website Chunking Ingest

Website Chunking Ingest

openai-chatgptlangchain-pythonchatgptgenaielasticsearchelasticingestion-and-chunkingopenaiAIchatlogvectordatabasenotebooksPythonsearchgenaistackvectorelasticsearch-labslangchainapplications

Website load, Extraction and Ingest with ELSER Example

Open In Colab

This workbook demonstrates how to load a website, create passages and ingest into Elasticsearch.

In this example we will:

  • load the website using the unstructured package
  • chunk the text with LangChain document splitter
  • ingest into Elasticsearch with LangChain Elasticsearch Vectorstore.

We will also setup your Elasticsearch cluster with ELSER model, so we can use it to embed the passages.

[ ]

Connecting to Elasticsearch

[3]

Deploying ELSER

[ ]

Loading a webpage, creating chunks into docs

This will load the webpage from the url provided, and then chunk the html text into passage docs.

[8]

Ingesting the passages into Elasticsearch

This will ingest the passage docs into the Elasticsearch index, under the specified INDEX_NAME.

[ ]