Contextual provides a platform for creating enterprise-grade AI agents, grounded in your documents and data. See a demo of our agents here. Our integrated system allows you to easily:
  • Parse and ingest documents into a fully managed vector store(s)
  • Create specialized agents that can answer questions and complete tasks by fetching relevant knowledge from your datastores
With Contextual, you get:
  • Best-in-class parsing capabilites and powerful chunking options that make wrangling unstructured data for RAG a breeze
  • Seamless orchestration of powerful RAG components and primitives, allowing you to build RAG agents that have exceptional accuracy and scalability
  • State-of-the-art capabilities and models, like our:
You can leverage our platform via our user-friendly UI or through our APIs and SDKs. Follow this guide to create your first agent! Or, see https://github.com/ContextualAI/examples for easy-to-follow Jupyter notebooks for using our APIs.

​
Get your API Key

Note: If you do not have access to the platform, you can create a workspace via the Start Free button in the upper right of the page. New workspaces are given $25 in free credits to trial the platform. Contextual uses API keys to authenticate requests. Only admins within a workspace can create API keys. To create a key:
  1. Log into your tenant at app.contextual.ai
  2. Click on API Keys in the sidebar
  3. Click the Create API Key button in the upper right and follow the instructions
  4. Save the generated key in a secure location

​
Create and query your first agent

​
Step 1: Create a datastore

Datastores contain the files that your agent(s) can access. Each agent must be associated with at least one datastore. You can create a datastore using the /datastores endpoint with the following command: 
from contextual import ContextualAI

# Initialize the client with your API key
contextual = ContextualAI(api_key="API_KEY")

# Create a datastore
datastore = contextual.datastores.create(name="Test Datastore")
Remember to replace $API_KEY with your key. You can rename the datastore if you want.
If the request is successful, the id of the newly created datastore will be returned to you. Be sure to save this id as you will need it in subsequent steps!

​
Step 2: Add documents into your datastore

Now that you’ve created a datastore, you can add documents to it. All documents are stored securely in the Contextual platform, and are parsed in ways optimized for use in RAG pipelines and Agents.
  • If you don’t have your own documents handy, feel free to use our Beginner’s Guide test documents, found here
  • For the best results, use renderable PDFs, i.e., documents that have text that can be copied and pasted.
You can upload a single document using the following command: 
from contextual import ContextualAI

# Initialize the client with your API key
contextual = ContextualAI(api_key="API_KEY")

# Upload a document
with open('file.pdf', 'rb') as f:
    ingestion_result = contextual.datastores.documents.ingest(datastore_id, file=f)
    document_id = ingestion_result.id
    print(f"Successfully uploaded document_id: {document_id} to datastore_id: {datastore_id}")
Remember to:
  • Replace {datastore_id} in the url path with the datastore id from the previous step
  • Replace $API_KEY with your API key
  • Replace {file_path} with the path to the document on your machine
If the request is successful, the id of the uploaded document will be returned to you. The time required to upload documents depends partly on their length and features. Some documents may require a few minutes to fully process after upload. To check the status of documents uploaded into the datastore, use this command: 
from contextual import ContextualAI

# Initialize the client with your API key
contextual = ContextualAI(api_key="API_KEY")

# Get the status of documents in the datastore
metadata = contextual.datastores.documents.metadata(datastore_id=datastore_id, document_id=document_id)
print("Document metadata:", metadata)
Remember to:
  • Replace {datastore_id} in the url path with the id from the previous step
  • Replace $API_KEY with your API key
You should see the document you uploaded in the list, along with its ingestion_job_status.

​
Step 3: Create an agent

Now that you have a datastore with some files, you can use the /agents endpoint to create your first agent. 
from contextual import ContextualAI

# Initialize the client with your API key
contextual = ContextualAI(api_key="API_KEY")

# Create an agent
agent = contextual.agents.create(name="Test Agent", description="Test Agent", datastore_ids=[datastore_id])
Remember to:
  • Replace $API_KEY with your API key
  • Populate the datastore_ids list field with the datastore id from above
If the request is successful, the agent_id of the newly created agent will be returned to you. You’ll need this to query your agent in the next step.

​
Step 4: Query your agent

Now that you’ve set up an agent and uploaded documents for use with it to use, you can use the /query endpoint to send messages: 
from contextual import ContextualAI

# Initialize the client with your API key
contextual = ContextualAI(api_key="API_KEY")

# Query the agent
response = contextual.agents.query.create(
  agent_id=agent_id,
  messages=[
    {
      "role": "user",
      "content": "What is the revenue of Apple?"
    }]
)
Remember to:
  • Replace {agent_id} in the url path with the agent_id from the previous step
  • Replace $API_KEY with your API key
  • Replace the content field with a question that is relevant to the document(s) you uploaded
If the request is successful, you’ll receive a response back that will contain:
  • The body of the response
  • The sources retrieved from the datastore that are relevant to the response
  • Attributions/citations of sources to specific text spans in the response
Note: You can only query your agent once at least one document in the datastore has been processed. You can check the status of uploaded documents by following the instructions in the previous step. 🙌 Congratulations! You’ve now created a basic agent in the Contextual platform.

​
Try out additional functionality

Now that you have a basic working agent, explore our advanced features:

Learn about advanced query features, like multi-turn and structured outputs