AI Detection & Response SDK to monitor and protect agentic applications
Project description
Evoke SDK
AI Observability SDK for tracking LLM execution and agent workflows.
Features
- Automatic tracing: Works with any LLM provider (OpenAI, Anthropic, custom)
- Zero code changes: Just initialize and go
- Comprehensive telemetry: Tracks tools, models, prompts, reasoning
- Simple API: 2 lines of code
Installation
pip install evoke-sdk
Quick Start
import evoke
# Initialize once at startup
evoke.init(api_key="evoke_pk_your_api_key")
# All LLM calls are now automatically traced!
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Hello!"}]
)
What Gets Tracked
- Models: Which models were used (gpt-4, claude-3, etc.)
- Prompts & Responses: Full input and output data
- Tools: Which tools/functions were called
- Knowledge Bases: Which vector stores/retrievers were accessed
- Reasoning: Agent thinking and decision-making
- Tokens: Input/output/cached token counts
- Timing: Duration and timestamps
- Errors: Exceptions and stack traces
Optional: Explicit Tracing
Use the @trace decorator for high-level workflows:
import evoke
@evoke.trace(name="customer_support_agent")
def handle_customer_query(query: str):
# Your agent logic
return agent.run(query)
Optional: Add Custom Context
Link telemetry to business entities:
@evoke.trace(name="process_order")
def process_order(order_id: str, user_id: str):
evoke.add_context(
user_id=user_id,
order_id=order_id,
environment="production"
)
return process()
Flush Before Exit
Ensure all data is sent before your app exits:
import evoke
# At the end of your script
evoke.flush()
Supported Frameworks
- OpenAI SDK
- Anthropic SDK
- LangChain
- LlamaIndex
- Any custom LLM implementation
Configuration
Environment Variables
export EVOKE_API_KEY="evoke_pk_your_key"
export EVOKE_ENDPOINT="https://api.evoke.com/v1/traces"
Debug Mode
evoke.init(
api_key="evoke_pk_...",
debug=True # Enable debug logging
)
License
Other/Proprietary License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
evoke_sdk-0.1.0.tar.gz
(46.1 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
evoke_sdk-0.1.0-py3-none-any.whl
(67.0 kB
view details)
File details
Details for the file evoke_sdk-0.1.0.tar.gz.
File metadata
- Download URL: evoke_sdk-0.1.0.tar.gz
- Upload date:
- Size: 46.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
90eb5311c70f772d87c61d389f2f114d9f58e0eb0896732141309ccf09c7476c
|
|
| MD5 |
1e94a3bcdc3617d0be0baaaaa27fdf88
|
|
| BLAKE2b-256 |
48f97aec3916f91388b6d2b3f055e22a911a5896084e35226f60e9a00214629e
|
File details
Details for the file evoke_sdk-0.1.0-py3-none-any.whl.
File metadata
- Download URL: evoke_sdk-0.1.0-py3-none-any.whl
- Upload date:
- Size: 67.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
161f2f23fad879ca78d7d6cefe7da8b53869733ccff17af64d1c8d52b2e3f464
|
|
| MD5 |
7e941378f93e3367558b5d9ad650fb48
|
|
| BLAKE2b-256 |
92a4c25e08a0dce32b62c82635fa38b620d94a631339df39ae65001d885f02dd
|