As a sensible instance, this text reveals the way to construct an AI Product assistant — an AI chatbot able to answering product-related questions utilizing knowledge from a number of sources. With the AI Product Assistant, you possibly can ask questions throughout all of your firm’s knowledge in a single place.
You possibly can make the most of the Snowflake Cortex vacation spot to load vector knowledge into Snowflake, adopted by leveraging Snowflake’s Cortex capabilities to carry out Retrieval-Augmented Technology (RAG). Cortex presents general-purpose ML capabilities and LLM-specific capabilities, together with vector capabilities for semantic search, every backed by a number of fashions, all with no need to handle or host the underlying fashions or infrastructure.
With Airbyte’s newly launched Snowflake Cortex vacation spot, customers can create their very own devoted vector retailer straight inside Snowflake — with no coding required! Creating a brand new pipeline with Snowflake Cortex takes just a few minutes, permitting you to load any of the 300-plus knowledge sources into your new Snowflake-backed vector retailer.
We are going to use the next three knowledge sources particular to Airbyte:
- Airbyte’s official documentation for the Snowflake Cortex vacation spot
- GitHub points, documenting deliberate options, identified bugs, and work in progress.
- Zendesk tickets comprising buyer particulars and inquiries/requests
RAG Overview
LLMs are general-purpose instruments skilled on an unlimited corpus of information, permitting them to reply questions on virtually any subject. Nonetheless, in case you are trying to extract info out of your proprietary knowledge, LLMs fall brief, resulting in potential inaccuracies and hallucinations. That is the place RAG turns into tremendous related. RAG addresses this limitation by enabling LLMs to entry related and up-to-date knowledge from any knowledge supply. The LLM can then use this info to reply related questions on your proprietary knowledge.
Conditions
To observe via the entire course of, you have to the next accounts. You can even work with your individual customized sources or work with a single supply:
- Airbyte cloud occasion
- Snowflake account with Cortex capabilities enabled
- Open AI
- Supply-specific: Google Drive, GitHub and Zendesk
Step 1: Arrange Snowflake Cortex Vacation spot
To pick a vacation spot in Airbyte Cloud, click on on the Locations tab on the left, choose “New Destination” and filter for the vacation spot you might be in search of.
Configure the Snowflake Cortex vacation spot in Airbyte:
- Vacation spot identify: Present a pleasant identify.
- Processing: Set chunk dimension to 1000 (the dimensions refers back to the variety of tokens, not characters, so that is roughly 4KB of textual content. The perfect chunking depends on the info you might be coping with). You possibly can depart different choices empty. You’ll normally set the metadata and textual content fields to restrict the studying of data to particular columns in a given stream.
- Embedding: Choose OpenAI from the dropdown and supply your OpenAI API key for powering the embedding service. You need to use some other obtainable fashions additionally. Simply bear in mind to embed the questions you ask the product assistant with the identical mannequin.
- Indexing: Present credentials for connecting to your Snowflake occasion.
Step 2: Arrange Google Drive, GitHub, and Zendesk Sources
To pick a supply, click on on the sources tab on the left, choose “New Source” and filter for the supply you might be in search of.
Google Drive
Choose Google Drive on the sources web page and configure the Google Drive supply. You have to to authenticate and supply the next:
- Folder URL: Present a hyperlink to your Google Drive folder. For this tutorial, you possibly can transfer the snowflake-cortex.md file from right here over to your Google Drive. Alternatively, you should utilize your individual file. Confer with the accompanying documentation to find out about legitimate file codecs.
- The listing of streams to sync
- Format: Set the format dropdown to “Document File Type Format”
- Identify: Present a stream identify.
GitHub
Choose GitHub on the sources web page and configure the GitHub supply. You have to to authenticate together with your GitHub account and supply the next:
- GitHub repositories: You need to use the repo:
airbytehq/PyAirbyteor present your individual.
Zendesk
Elective: Choose Zendesk on the sources pages and configure the Zendesk supply. It is possible for you to to authenticate utilizing OAuth, or API token, and supply the next:
- Sub-domain identify: in case your Zendesk account URL is https://MY_SUBDOMAIN.zendesk.com/, then
MY_SUBDOMAINis your subdomain.
After you might have arrange all sources, that is what your supply display screen will seem like:
Step 3: Arrange All Connections
Subsequent, we’ll arrange the next connections:
- Google Drive → Snowflake Cortex
- Github → Snowflake Cortex
- Zendesk → Snowflake Cortex
Google Drive → Snowflake Cortex
Choose the Connections tab on the left navigation in Airbyte Cloud; then click on on “New connection” on the highest proper.
- Within the configuration move, choose the present Google Drive supply and Snowflake Cortex because the vacation spot.
- On the choose streams display screen, choose
Full Refresh|Overwritebecause the sync mode. - On the configure connection, choose the Schedule sort to each 24 hours. Optionally present a stream prefix on your desk. In our case we prefix airbyte_ to all streams.
- Click on on End and Sync.
- If all the things went properly, there ought to be a connection now synching knowledge from Google Drive to Snowflake Cortex vacation spot. Give the sync a couple of minutes to run. As soon as the primary run has been accomplished, you possibly can examine Snowflake to verify knowledge sync. The info ought to be synched below a desk named “[optional prefix][stream name]”
Github → Snowflake Cortex
Choose the Connections tab on the left navigation in Airbyte Cloud; then click on on “New connection” on the highest proper.
- Within the configuration move, choose the present Github supply and Snowflake Cortex because the vacation spot.
- On the choose streams display screen, be certain that all streams besides
pointsare unchecked. Additionally, set the sync mode toFull Refresh|Overwrite. - On the configure connection display screen, choose the Schedule sort each 24 hours. Optionally present a stream prefix on your desk. In our case, we prefix airbyte_ to all streams.
- Click on on End and Sync.
- If all the things goes properly, there ought to be a connection now synching knowledge from GitHub to the Snowflake Cortex vacation spot. Give the sync a couple of minutes to finish. As soon as the primary run has been accomplished, you possibly can examine Snowflake to verify knowledge sync. The info ought to be synched below a desk named “[optional prefix]issues”
Zendesk → Snowflake Cortex
Choose the Connections tab on the left navigation in Airbyte Cloud; then click on on “New connection” on the highest proper.
- Within the configuration move, choose the present Zendesk supply and Snowflake Cortex because the vacation spot.
- On the choose streams display screen, be certain that all streams besides
ticketsandcustomersare unchecked. Additionally, set the sync mode toFull Refresh | Overwrite. - On the configure connection display screen, choose the Schedule sort to each 24 hours. Optionally present a stream prefix on your desk. In our case, we prefix
airbyte_to all streams. - Click on on End and Sync.
- If all the things goes properly, there ought to be a connection now synching knowledge from Zendesk to the Snowflake Cortex vacation spot. Give the sync a couple of minutes to finish. As soon as the primary run has been accomplished, you possibly can examine Snowflake to verify knowledge sync. The info ought to be synched below a desk named “[optional prefix]tickets” and ““[optional prefix]tickets”
As soon as all of the three connections are set, the Connections display screen ought to seem like this.
Step 4: Discover Knowledge in Snowflake
It’s best to see the next tables in Snowflake. Relying in your stream prefix, your desk names could be totally different.
- Google Drive associated:
airbyte_docs - GitHub associated:
airbyte_github_issues - Zendesk associated:
airbyte_zendesk_tickets,airbyte_zendesk_users
All tables have the next columns
DOCUMENT_ID: Distinctive primarily based on main keyCHUNK_ID: Randomly generated uuidDOCUMENT_CONTENT: Textual content context from supplyMETADATA: Metadata from supplyEMBEDDING: Vector illustration of the document_content
Outcomes from one among these tables ought to seem like the next:
Step 5: RAG Constructing Blocks
On this part, we’ll go over the important constructing blocks of a Retrieval-Augmented Technology (RAG) system. This includes embedding the person’s query, retrieving matching doc chunks, and utilizing a language mannequin to generate the ultimate reply. Step one is completed utilizing OpenAI, and the second and third steps are achieved utilizing Snowflake’s Cortex capabilities. Let’s break down these steps:
5.1 Embedding Person’s Query
When a person asks a query, it is essential to remodel the query right into a vector illustration utilizing the identical mannequin employed for producing vectors within the vector database. On this instance, we use Langchain to entry and use OpenAI’s embedding mannequin. This step ensures that the query is represented in a format that may be successfully in contrast with doc vectors.
5.2 Retrieving Matching Chunks
The embedded query is then despatched to Snowflake, the place doc chunks with comparable vector representations are retrieved. All related chunks are returned.
5.3 Passing Chunks to LLM for a Ultimate Reply
All of the chunks are concatenated right into a single string and despatched to the Snowflake (utilizing Snowflake Python Connector) together with a immediate (set of directions) and the person’s query.
Step 6: Placing It All Collectively
Google Colab
For comfort, we’ve got built-in all the things right into a Google Collab pocket book. Discover the totally purposeful RAG code in Google Colab.
Each time a query is requested, we move the listing of related tables and fashions. For the primary query beneath, the reply is retrieved from Airbyte docs solely, whereas, for the second query, the reply is retrieved from GitHub points.
You can even present a number of tables as enter, and the ensuing response will probably be a mix of information from each sources.
Streamlit App
We’ve additionally built-in the above RAG performance right into a Streamlit chat app. Discover the totally purposeful code on GitHub.
Conclusion
Utilizing the LLM capabilities of Snowflake Cortex together with Airbyte’s catalog of 300-plus connectors, you possibly can construct an insightful AI assistant to reply questions throughout a lot of knowledge sources. We’ve saved issues easy right here, however as your variety of sources will increase, take into account integrating an AI agent to interpret person intent and retrieve solutions from the suitable supply.