Pinecone Assistant: SDK quickstart

Quickstart for Pinecone Assistant using the Python or Node.js SDK to create an assistant, upload documents, and chat with your data via RAG.

Use a Pinecone SDK to create an assistant, upload documents, and chat with the assistant.

1. Install an SDK

The Pinecone Python SDK and Node.js SDK provide convenient programmatic access to the Assistant API.

Python

pip install pinecone
pip install pinecone-plugin-assistant

JavaScript

npm install @pinecone-database/pinecone

2. Get an API key

You need an API key to make calls to your assistant.

Create a new API key in the Pinecone console, or use the widget below to generate a key. If you don't have a Pinecone account, the widget will sign you up for the free Starter plan.

Your generated API key:

Shell

"{{YOUR_API_KEY}}"

3. Create an assistant

Create an assistant, as in the following example:

Python

from pinecone import Pinecone

pc = Pinecone(api_key="{{YOUR_API_KEY}}")

assistant = pc.assistant.create_assistant(
    assistant_name="example-assistant", 
    instructions="Use American English for spelling and grammar.", # Description or directive for the assistant to apply to all responses.
    region="us", # Region to deploy assistant. Options: "us" (default) or "eu".
    timeout=30 # Maximum seconds to wait for assistant status to become "Ready" before timing out.
)

JavaScript

import { Pinecone } from '@pinecone-database/pinecone'

const pc = new Pinecone({ apiKey: "{{YOUR_API_KEY}}" });

const assistant = await pc.createAssistant({
  name: 'example-assistant',
  instructions: 'Use American English for spelling and grammar.', // Description or directive for the assistant to apply to all responses.
  region: 'us'
});

4. Upload a file to the assistant

With Pinecone Assistant, you can upload documents, ask questions, and receive responses that reference your documents. This is known as retrieval-augmented generation (RAG).

For this quickstart, download a sample 10-k filing file to your local device.

Next, upload the file to your assistant:

Python

# Get the assistant.
assistant = pc.assistant.Assistant(
    assistant_name="example-assistant", 
)

# Upload a file.
response = assistant.upload_file(
    file_path="/path/to/file/Netflix-10-K-01262024.pdf",
    metadata={"company": "netflix", "document_type": "form 10k"},
    timeout=None
)

JavaScript

const assistantName = 'example-assistant';
const assistant = pc.Assistant(assistantName);

await assistant.uploadFile({
  path: '/Users/jdoe/Downloads/example_file.txt'
});

5. Chat with the assistant

With the sample file uploaded, you can now chat with the assistant. Ask the assistant questions about your document. It returns either a JSON object or a text stream.

The following example requests a default response to the message, "Who is the CFO of Netflix?":

Python

from pinecone_plugins.assistant.models.chat import Message

msg = Message(role="user", content="Who is the CFO of Netflix?")
resp = assistant.chat(messages=[msg])

print(resp)

JavaScript

const chatResp = await assistant.chat({
  messages: [{ role: 'user', content: 'Who is the CFO of Netflix?' }],
  model: 'gpt-4o'
});

console.log(chatResp);

The example above returns a response like the following:

{
    'id': '0000000000000000163008a05b317b7b', 
    'model': 'gpt-4o-2024-05-13', 
    'usage': {
        'prompt_tokens': 9259, 
        'completion_tokens': 30, 
        'total_tokens': 9289
        }, 
        'message': {
            'content': 'The Chief Financial Officer (CFO) of Netflix is Spencer Neumann.', 
            'role': '"assistant"'
            }, 
            'finish_reason': 'stop', 
            'citations': [
                {
                    'position': 63, 
                    'references': [
                        {
                            'pages': [78, 72, 79], 
                            'file': {
                                'name': 'Netflix-10-K-01262024.pdf', 
                                'id': '76a11dd1...', 
                                'metadata': {
                                    'company': 'netflix', 
                                    'document_type': 'form 10k'
                                    }, 
                                    'created_on': '2024-12-06T01:29:07.369208590Z', 
                                    'updated_on': '2024-12-06T01:29:50.923493799Z', 
                                    'status': 'Available', 
                                    'signed_url': 'https://storage.googleapis.com/...',
                                    'size': 1073470.0
                                }
                            }
                        ]
                    }
                ]
            }

6. Clean up

When you no longer need the example-assistant, delete the assistant:

Python

pc.assistant.delete_assistant(
    assistant_name="example-assistant", 
)

JavaScript

await pc.deleteAssistant('example-assistant');

Next steps

Learn more about Pinecone Assistant
Learn about additional assistant features
Evaluate the assistant's responses
View a sample app that uses Pinecone Assistant