Upstash Async

Code

1import asyncio
2import os
3
4from kern.agent import Agent
5from kern.knowledge.knowledge import Knowledge
6from kern.vectordb.upstashdb import UpstashVectorDb
7
8# How to connect to an Upstash Vector index
9# - Create a new index in Upstash Console with the correct dimension
10# - Fetch the URL and token from Upstash Console
11# - Replace the values below or use environment variables
12
13vector_db = UpstashVectorDb(
14    url=os.getenv("UPSTASH_VECTOR_REST_URL"),
15    token=os.getenv("UPSTASH_VECTOR_REST_TOKEN"),
16)
17
18# Initialize Upstash DB
19knowledge = Knowledge(
20    name="Basic SDK Knowledge Base",
21    description="Kern 2.0 Knowledge Implementation with Upstash Vector DB",
22    vector_db=vector_db,
23)
24
25# Create and use the agent
26agent = Agent(knowledge=knowledge)
27
28if __name__ == "__main__":
29    # Comment out after first run
30    asyncio.run(
31        knowledge.ainsert(
32            name="Recipes",
33            url="https://kern-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
34            metadata={"doc_type": "recipe_book"},
35        )
36    )
37
38    # Create and use the agent
39    asyncio.run(
40        agent.aprint_response("How to make Pad Thai?", markdown=True)
41    )

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Install dependencies

1uv pip install -U upstash-vector pypdf openai kern-ai

Set environment variables

1export UPSTASH_VECTOR_REST_URL="your-upstash-vector-rest-url"
2export UPSTASH_VECTOR_REST_TOKEN="your-upstash-vector-rest-token"
3export OPENAI_API_KEY=xxx

Run Agent

1python cookbook/08_knowledge/vector_db/upstash_db/upstash_db.py