Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.memic.ai/llms.txt

Use this file to discover all available pages before exploring further.

This guide takes you from zero to a working search query against your own content. You’ll need Python 3.10+ and a Memic API key from the dashboard.

​
1. Install the SDK

pip install memic

​
2. Authenticate

All Memic API calls are authenticated with an API key. Get one from your environment’s API keys page in the dashboard, then set it as an environment variable: 
export MEMIC_API_KEY="mk_live_..."
The SDK picks it up automatically. You can also pass it explicitly: 
from memic import Memic

client = Memic(api_key="mk_live_...")
Every API key is bound to exactly one environment (e.g. staging or production). Swap the key to swap environments — no code changes.

​
3. Verify your connection

from memic import Memic

client = Memic()
print(client.me())
# ApiKeyInfo(organization_name='...', project_name='...', environment_slug='production')
If this returns your org and project, you’re authenticated correctly.

​
4. Upload a file

Memic’s upload flow uses presigned URLs so large files go directly to storage without passing through the API server. The SDK handles both steps for you: 
result = client.files.upload("./product-handbook.pdf")
print(result.file_id)
The file is queued for processing (chunking, embedding, indexing). You can poll for status: 
status = client.files.get_status(result.file_id)
print(status.status)  # pending → processing → ready
Typical processing time for a PDF is under 30 seconds.

​
5. Search your content

Once the file is ready, semantic search works immediately: 
results = client.search("what is our refund policy")

for hit in results.semantic:
    print(f"[{hit.score:.2f}] {hit.text[:200]}...")
    print(f"   from {hit.source.file_name}")

​
6. Chat over your content

Search returns passages; chat returns grounded answers: 
response = client.chat("Summarize our refund policy in three bullet points")

print(response.answer)
for citation in response.citations:
    print(f"  → {citation.file_name} (p. {citation.page})")

​
Next steps

Guide: Ingestion

Batch uploads, metadata, folder organization.

Guide: Search

Filters, top-k tuning, hybrid retrieval.

Recipe: Chatbot

Build a customer-facing chat over your docs.

API Reference

Every endpoint, every parameter.