{% columns %}
{% column %}
#### Plug Graffo into your agent stack fast
Query your collections with a single call. Use curl for quick tests or the Python SDK when shipping agents and backends.
Give your AI agents the context they need. Connect disparate data sources, visualize complex relationships, and query with semantic precision.
Get startedAPI reference
{% endcolumn %}
{% column %}
{% code title="graffo-sdk.py" overflow="wrap" %}
```python
from graffo import GraffoSDK, SearchRequest
client = GraffoSDK(
api_key="YOUR_API_KEY",
organization_id="YOUR_ORG_ID",
)
resp = client.collections.search(
readable_id="your-collection",
request=SearchRequest(query="summaries of meeting notes", limit=5)
)
print(resp.results)
```
{% endcode %}
{% endcolumn %}
{% endcolumns %}
{% columns %}
{% column %}
{% endcolumn %}
{% column %}
#### Built for teams who need reliable context in every AI decision
Whether you are prototyping your first agent or scaling retrieval for thousands of users, Graffo keeps your knowledge connected and queryable.
GuidesDocumentation
{% endcolumn %}
{% endcolumns %}
Who is Graffo for?
Built for teams who need reliable context in every AI decision.
:robot:
AI agent builders
Give your agents a structured world model so tool calls stay grounded and actions remain consistent.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.graffo.io/readme.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
