> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usetrident.dev/llms.txt
> Use this file to discover all available pages before exploring further.
# Install the Trident Python SDK (vouch-sdk)
> Install vouch-sdk and instrument Python AI agents, LangChain, CrewAI, and more with Trident observability and security in one call.
The `vouch-sdk` package wraps OpenLLMetry auto-instrumentation and points it at your Trident project. One call to `vouch_sdk.init()` patches every LLM client loaded in your Python process — OpenAI, Anthropic, LangChain, CrewAI, LlamaIndex, Bedrock, VertexAI, Cohere, and more — and ships the resulting OpenTelemetry spans to [app.usetrident.dev](https://app.usetrident.dev). PII redaction runs entirely inside your runtime before any trace data leaves, keeping emails, API keys, credit card numbers, and other sensitive values out of the wire.
## Requirements
* **Python 3.10 or later**
* pip
## Install
```bash theme={null}
pip install vouch-sdk
```
The base package instruments OpenAI, Anthropic, LlamaIndex, Bedrock, VertexAI, Cohere, MCP, and the OpenAI Agents SDK out of the box.
Add the `[langchain]` extra to enable LangChain and CrewAI instrumentation:
```bash theme={null}
pip install "vouch-sdk[langchain]"
```
| Extra | Installs | Enables |
| ----------- | -------------------------- | ------------------------------------ |
| `langchain` | `langchain-core>=0.2,<1.0` | LangChain chains, agents, and CrewAI |
## Set your environment variables
Add your project keys from **Settings → API Keys** at [app.usetrident.dev](https://app.usetrident.dev) to your `.env` file or deployment secrets manager:
```bash .env theme={null}
TRIDENT_PROJECT_PUBLIC_KEY=pk-...
TRIDENT_PROJECT_SECRET_KEY=sk-...
```
The SDK also accepts the legacy `VOUCH_PROJECT_PUBLIC_KEY` / `VOUCH_PROJECT_SECRET_KEY` names for backwards compatibility.
## Initialize Trident
Call `vouch_sdk.init()` **once**, before you create any LLM client. Every LLM call made after `init()` is automatically traced.
```python theme={null}
import vouch_sdk
vouch_sdk.init(
agent_id="prod-rag-bot", # optional — scopes spans to a named agent
)
```
When `project_pk` and `project_sk` are omitted, `init()` reads them from `TRIDENT_PROJECT_PUBLIC_KEY` / `TRIDENT_PROJECT_SECRET_KEY` automatically.
### All options
| Parameter | Type | Default | Description |
| -------------------- | -------------- | ------------------------- | ------------------------------------------------------------------------------------------------------------------ |
| `project_pk` | `str` | env | Project public key. Reads `TRIDENT_PROJECT_PUBLIC_KEY`. |
| `project_sk` | `str` | env | Project secret key. Reads `TRIDENT_PROJECT_SECRET_KEY`. |
| `agent_id` | `str` | env | Logical agent identifier shown in the dashboard. Reads `TRIDENT_AGENT_ID`. |
| `endpoint` | `str` | `https://app.tryvouch.ai` | Override the Trident host. Reads `TRIDENT_ENDPOINT`. |
| `agent_url` | `str` | env | Public HTTP endpoint for Red Team auto-targeting. Reads `VOUCH_AGENT_URL`. |
| `app_name` | `str` | `agent_id` | OTel resource `service.name`. Falls back to `"vouch-app"`. |
| `disable_batch` | `bool` | `False` | Emit each span immediately. Useful for short-lived scripts. |
| `instruments` | `set` | `None` | Restrict which traceloop instruments are activated. |
| `redact_pii` | `bool \| dict` | `True` | Edge PII redaction. `True` uses the built-in rule set; pass `{"rules": [...]}` for custom rules; `False` disables. |
| `**traceloop_kwargs` | | | Extra keyword arguments forwarded verbatim to `Traceloop.init()`. |
## Full working example
The snippet below starts Trident tracing and makes a standard OpenAI chat completion. The call is traced automatically — no wrapping required.
```python theme={null}
import os
import vouch_sdk
from openai import OpenAI
# 1. Start tracing — do this before creating any LLM client.
vouch_sdk.init(
agent_id="my-chat-agent",
# project_pk and project_sk are read from env automatically
)
# 2. Create your LLM client exactly as you normally would.
client = OpenAI() # picks up OPENAI_API_KEY from env
# 3. Make LLM calls — tracing is automatic.
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Summarise the Trident docs in one sentence."}],
)
print(response.choices[0].message.content)
```
## LangChain example
Install the `langchain` extra, then call `init()` before building your chain:
```python theme={null}
import vouch_sdk
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
vouch_sdk.init(agent_id="langchain-agent")
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful assistant."),
("human", "{question}"),
])
chain = prompt | llm
result = chain.invoke({"question": "What is prompt injection?"})
print(result.content)
```
Every chain invocation, LLM call, and retrieval step is automatically captured as a nested OTel span in your Trident project.
## Supported LLM frameworks
The SDK auto-instruments all of the following when they are imported in the same process:
LangChain and CrewAI require the `[langchain]` extra: `pip install "vouch-sdk[langchain]"`.
## PII redaction defaults
`redact_pii=True` is the default. Before any span attribute leaves your process, the SDK scans and replaces the following patterns with `[REDACTED_]` tokens:
* **EMAIL** — email addresses
* **AWS\_KEY** — AWS access key IDs (`AKIA…`, `ASIA…`)
* **JWT** — JSON Web Tokens
* **API\_KEY** — API keys (`sk-…`, `sk-ant-…`)
* **SSN** — US Social Security Numbers (`XXX-XX-XXXX`)
* **CREDIT\_CARD** — credit card numbers (Luhn-validated)
* **IBAN** — International Bank Account Numbers
* **IP** — IPv4 addresses
* **PHONE** — phone numbers
Pass `redact_pii=False` to disable, or `redact_pii={"rules": [...]}` to supply a custom list of `PiiRule` objects.
## Next steps
Explore the full API: `vouch_sdk.init()`, `firewall_headers()`, `redact_text()`, `redact_value()`, and all configuration options.