> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/Arize-ai/openinference/llms.txt
> Use this file to discover all available pages before exploring further.

# Environment Variables

> Configure OpenInference tracing behavior using environment variables

# Environment Variables

OpenInference supports configuration through environment variables, providing a convenient way to control tracing behavior without modifying your code.

## Overview

Environment variables allow you to:

* Configure tracing behavior globally across your application
* Adjust observability levels between different environments (dev, staging, production)
* Control privacy and security settings without code changes

## Configuration Precedence

When both environment variables and TraceConfig are used:

1. Values set in TraceConfig objects (highest priority)
2. Environment variables
3. Default values (lowest priority)

## Supported Variables

### Input/Output Controls

| Variable                             | Type | Default | Description                                                                                                                       |
| ------------------------------------ | ---- | ------- | --------------------------------------------------------------------------------------------------------------------------------- |
| `OPENINFERENCE_HIDE_INPUTS`          | bool | `False` | Hides input.value and all input messages. Input messages are hidden if either `HIDE_INPUTS` OR `HIDE_INPUT_MESSAGES` is true      |
| `OPENINFERENCE_HIDE_OUTPUTS`         | bool | `False` | Hides output.value and all output messages. Output messages are hidden if either `HIDE_OUTPUTS` OR `HIDE_OUTPUT_MESSAGES` is true |
| `OPENINFERENCE_HIDE_INPUT_MESSAGES`  | bool | `False` | Hides all input messages (independent of `HIDE_INPUTS`)                                                                           |
| `OPENINFERENCE_HIDE_OUTPUT_MESSAGES` | bool | `False` | Hides all output messages (independent of `HIDE_OUTPUTS`)                                                                         |

### Message Content Controls

| Variable                          | Type | Default | Description                                                                                |
| --------------------------------- | ---- | ------- | ------------------------------------------------------------------------------------------ |
| `OPENINFERENCE_HIDE_INPUT_IMAGES` | bool | `False` | Hides images from input messages (only applies when input messages are not already hidden) |
| `OPENINFERENCE_HIDE_INPUT_TEXT`   | bool | `False` | Hides text from input messages (only applies when input messages are not already hidden)   |
| `OPENINFERENCE_HIDE_OUTPUT_TEXT`  | bool | `False` | Hides text from output messages (only applies when output messages are not already hidden) |

### LLM-Specific Controls

| Variable                                       | Type | Default | Description                                                          |
| ---------------------------------------------- | ---- | ------- | -------------------------------------------------------------------- |
| `OPENINFERENCE_HIDE_LLM_INVOCATION_PARAMETERS` | bool | `False` | Hides LLM invocation parameters (independent of input/output hiding) |
| `OPENINFERENCE_HIDE_PROMPTS`                   | bool | `False` | Hides LLM prompts (completions API)                                  |
| `OPENINFERENCE_HIDE_CHOICES`                   | bool | `False` | Hides LLM choices (completions API outputs)                          |

### Embedding Controls

| Variable                                | Type | Default | Description                                                                    |
| --------------------------------------- | ---- | ------- | ------------------------------------------------------------------------------ |
| `OPENINFERENCE_HIDE_EMBEDDINGS_VECTORS` | bool | `False` | Replaces embedding.embeddings.\*.embedding.vector values with `"__REDACTED__"` |
| `OPENINFERENCE_HIDE_EMBEDDINGS_TEXT`    | bool | `False` | Replaces embedding.embeddings.\*.embedding.text values with `"__REDACTED__"`   |
| `OPENINFERENCE_HIDE_EMBEDDING_VECTORS`  | bool | `False` | **Deprecated:** Use `OPENINFERENCE_HIDE_EMBEDDINGS_VECTORS` instead            |

### Size Limits

| Variable                                | Type | Default | Description                                                                                                             |
| --------------------------------------- | ---- | ------- | ----------------------------------------------------------------------------------------------------------------------- |
| `OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH` | int  | `32000` | Limits characters of a base64 encoding of an image. Images exceeding this length will be replaced with `"__REDACTED__"` |

## Usage Examples

### Bash/Shell

```bash theme={null}
# Hide all inputs and outputs
export OPENINFERENCE_HIDE_INPUTS=true
export OPENINFERENCE_HIDE_OUTPUTS=true

# Run your application
python app.py
```

### Docker

```dockerfile theme={null}
FROM python:3.11

# Set environment variables
ENV OPENINFERENCE_HIDE_INPUT_TEXT=true
ENV OPENINFERENCE_HIDE_OUTPUT_TEXT=true
ENV OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH=16000

COPY . /app
WORKDIR /app
RUN pip install -r requirements.txt

CMD ["python", "app.py"]
```

### Docker Compose

```yaml theme={null}
version: '3.8'
services:
  app:
    build: .
    environment:
      - OPENINFERENCE_HIDE_INPUTS=false
      - OPENINFERENCE_HIDE_OUTPUTS=false
      - OPENINFERENCE_HIDE_INPUT_IMAGES=true
      - OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH=16000
```

### Kubernetes

```yaml theme={null}
apiVersion: v1
kind: ConfigMap
metadata:
  name: openinference-config
data:
  OPENINFERENCE_HIDE_INPUT_TEXT: "true"
  OPENINFERENCE_HIDE_OUTPUT_TEXT: "true"
  OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH: "16000"
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: my-app
spec:
  template:
    spec:
      containers:
      - name: app
        image: my-app:latest
        envFrom:
        - configMapRef:
            name: openinference-config
```

### Python (.env file)

```python theme={null}
# .env
OPENINFERENCE_HIDE_INPUTS=false
OPENINFERENCE_HIDE_OUTPUTS=false
OPENINFERENCE_HIDE_INPUT_IMAGES=true
OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH=16000
```

```python theme={null}
# app.py
from dotenv import load_dotenv
load_dotenv()

# Environment variables are automatically picked up
from openinference.instrumentation.openai import OpenAIInstrumentor
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
```

### Node.js (.env file)

```bash theme={null}
# .env
OPENINFERENCE_HIDE_INPUTS=false
OPENINFERENCE_HIDE_OUTPUTS=false
OPENINFERENCE_HIDE_INPUT_IMAGES=true
OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH=16000
```

```typescript theme={null}
// app.ts
import { config } from "dotenv";
config();

// Environment variables are automatically picked up
import { OpenAIInstrumentation } from "@arizeai/openinference-instrumentation-openai";
const instrumentation = new OpenAIInstrumentation();
```

## Boolean Values

Boolean environment variables accept the following values (case-insensitive):

* `true`, `True`, `TRUE` → `true`
* `false`, `False`, `FALSE` → `false`
* Any other value → defaults to `false`

## Integer Values

Integer environment variables (like `OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH`):

* Must be valid integer strings (e.g., `"16000"`, `"32000"`)
* Invalid values will fall back to the default value
* In Java, can also be set to `"unlimited"` for no limit

## Common Scenarios

### Development Environment

```bash theme={null}
# Maximum observability - see everything
export OPENINFERENCE_HIDE_INPUTS=false
export OPENINFERENCE_HIDE_OUTPUTS=false
```

### Production Environment

```bash theme={null}
# Hide sensitive text but keep structure
export OPENINFERENCE_HIDE_INPUT_TEXT=true
export OPENINFERENCE_HIDE_OUTPUT_TEXT=true
export OPENINFERENCE_HIDE_EMBEDDINGS_TEXT=true
```

### Compliance Requirements

```bash theme={null}
# Hide all potentially sensitive data
export OPENINFERENCE_HIDE_INPUTS=true
export OPENINFERENCE_HIDE_OUTPUTS=true
export OPENINFERENCE_HIDE_EMBEDDINGS_VECTORS=true
export OPENINFERENCE_HIDE_EMBEDDINGS_TEXT=true
```

### Reduce Payload Size

```bash theme={null}
# Limit image sizes to reduce storage costs
export OPENINFERENCE_BASE64_IMAGE_MAX_LENGTH=8000
```

## Redacted Content

When content is hidden due to environment variable settings, the value `"__REDACTED__"` is used as a placeholder. This allows trace consumers to identify that content was intentionally hidden rather than missing or empty.

## Next Steps

* See [TraceConfig](/configuration/trace-config) for programmatic configuration
* See [Privacy Controls](/configuration/privacy-controls) for detailed privacy scenarios