mem0/notebooks/pinecone.ipynb

Cookbook for using PineconeDB with Embedchain

Step-1: Install embedchain package

In [ ]:

!pip install embedchain

In [ ]:

!pip install embedchain[dataloaders]

Step-2: Set environment variables needed for Pinecone and install the dependencies.

You can find this env variable on your OpenAI dashboard and Pinecone dashboard. Now lets install the dependencies needed for Pinecone.

In [ ]:

!pip install --upgrade 'embedchain[pinecone]'

In [ ]:

import os
from embedchain import Pipeline as App

os.environ["OPENAI_API_KEY"] = "sk-xxx"
os.environ["PINECONE_API_KEY"] = "xxx"
os.environ["PINECONE_ENV"] = "xxx"

Step-3: Define your Vector Database config

In [ ]:

config = """
vectordb:
  provider: pinecone
  config:
    metric: cosine
    vector_dimension: 768
    collection_name: pc-index
"""

# Write the multi-line string to a YAML file
with open('pinecone.yaml', 'w') as file:
    file.write(config)

Step-4 Create embedchain app based on the config

In [ ]:

app = App.from_config(yaml_path="pinecone.yaml")

Step-5: Add data sources to your app

In [ ]:

app.add("https://www.forbes.com/profile/elon-musk")

Step-6: All set. Now start asking questions related to your data

In [ ]:

while(True):
    question = input("Enter question: ")
    if question in ['q', 'exit', 'quit']:
        break
    answer = app.query(question)
    print(answer)