Skip to content

Commit 7a9b9ae

Browse files
siddharthsambharia-portkeysiddharthsambharia-portkey
committed
codex docs
1 parent 6746fe3 commit 7a9b9ae

File tree

1 file changed

+396
-0
lines changed

1 file changed

+396
-0
lines changed

‎integrations/libraries/codex.mdx

Lines changed: 396 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,396 @@
1+
---
2+
title: 'OpenAI Codex CLI'
3+
description: 'Add usage tracking, cost controls, and security guardrails to your Codex CLI deployment'
4+
---
5+
6+
OpenAI Codex CLI is a lightweight coding agent that runs directly in your terminal, letting you interact with AI to analyze, modify, and execute code in your projects. While Codex delivers powerful code generation and execution capabilities, Portkey adds essential enterprise controls for production deployments:
7+
8+
- **Unified AI Gateway** - Single interface for 250+ LLMs with API key management (beyond Codex's default model options)
9+
- **Centralized AI observability**: Real-time usage tracking for 40+ key metrics and logs for every request
10+
- **Governance** - Real-time spend tracking, set budget limits and RBAC in your Codex setup
11+
- **Security Guardrails** - PII detection, content filtering, and compliance controls
12+
13+
This guide will walk you through integrating Portkey with OpenAI Codex CLI and setting up essential enterprise features including usage tracking, access controls, and budget management.
14+
15+
<Note>
16+
If you are an enterprise looking to use Codex CLI in your organization, [check out this section](#3-set-up-enterprise-governance-for-codex).
17+
</Note>
18+
19+
# 1. Setting up Portkey
20+
Portkey allows you to use 250+ LLMs with your Codex CLI setup, with minimal configuration required. Let's set up the core components in Portkey that you'll need for integration.
21+
22+
<Steps>
23+
<Step title="Create Virtual Key">
24+
Virtual Keys are Portkey's secure way to manage your LLM provider API keys. Think of them like disposable credit cards for your LLM API keys, providing essential controls like:
25+
- Budget limits for API usage
26+
- Rate limiting capabilities
27+
- Secure API key storage
28+
29+
To create a virtual key:
30+
Go to [Virtual Keys](https://app.portkey.ai/virtual-keys) in the Portkey App. Save and copy the virtual key ID
31+
32+
<Frame>
33+
<img src="/images/integrations/openai/virtual-key-2.png" width="500"/>
34+
</Frame>
35+
36+
<Note>
37+
Save your virtual key ID - you'll need it for the next step.
38+
</Note>
39+
</Step>
40+
41+
<Step title="Create Default Config">
42+
43+
Configs in Portkey are JSON objects that define how your requests are routed. They help with implementing features like advanced routing, fallbacks, and retries.
44+
45+
We need to create a default config to route our requests to the virtual key created in Step 1.
46+
47+
To create your config:
48+
1. Go to [Configs](https://app.portkey.ai/configs) in Portkey dashboard
49+
2. Create new config with:
50+
```json
51+
{
52+
"virtual_key": "YOUR_VIRTUAL_KEY_FROM_STEP1",
53+
"override_params": {
54+
"model": "gpt-4o" // Your preferred model name
55+
}
56+
}
57+
```
58+
3. Save and note the Config name for the next step
59+
60+
<Frame>
61+
<img src="/images/integrations/config.png" width="500"/>
62+
</Frame>
63+
64+
<Note>
65+
This basic config connects to your virtual key. You can add more advanced portkey features later.
66+
</Note>
67+
</Step>
68+
69+
<Step title="Configure Portkey API Key">
70+
71+
Now create Portkey API key access point and attach the config you created in Step 2:
72+
73+
1. Go to [API Keys](https://app.portkey.ai/api-keys) in Portkey and Create new API key
74+
2. Select your config from `Step 2`
75+
3. Generate and save your API key
76+
77+
<Frame>
78+
<img src="/images/integrations/api-key.png" width="500"/>
79+
</Frame>
80+
81+
<Note>
82+
Save your API key securely - you'll need it for Codex CLI integration.
83+
</Note>
84+
</Step>
85+
</Steps>
86+
87+
# 2. Integrate Portkey with OpenAI Codex CLI
88+
89+
Now that you have your Portkey components set up, let's connect them to OpenAI Codex CLI. The integration leverages Codex's provider configuration options to route all requests through Portkey's AI Gateway.
90+
91+
<Note>
92+
You need your Portkey API Key from [Step 1](#1-setting-up-portkey) before going further.
93+
</Note>
94+
95+
## Using Portkey Configuration File
96+
97+
OpenAI Codex CLI supports a configuration file where you can specify your AI provider settings. Let's set up this configuration to use Portkey:
98+
99+
1. Create or edit the Codex configuration file at `~/.codex/config.json`:
100+
101+
```json
102+
{
103+
"provider": "portkey",
104+
"model": "gpt-4o",
105+
"providers": {
106+
"portkey": {
107+
"name": "Portkey",
108+
"baseURL": "https://api.portkey.ai/v1",
109+
"envKey": "PORTKEY_API_KEY"
110+
}
111+
}
112+
}
113+
```
114+
115+
2. Set your Portkey API key as an environment variable:
116+
117+
```shell
118+
export PORTKEY_API_KEY="your-portkey-api-key-here"
119+
```
120+
121+
> **Note:** This command sets the key only for your current terminal session. You can add the `export` line to your shell's configuration file (e.g., `~/.zshrc`) for persistence, or place it in a `.env` file at the root of your project.
122+
123+
3. Test your integration:
124+
125+
```shell
126+
codex "explain this repository to me"
127+
```
128+
129+
130+
# 3. Set Up Enterprise Governance for Codex
131+
132+
**Why Enterprise Governance?**
133+
If you are using Codex CLI inside your organization, you need to consider several governance aspects:
134+
- **Cost Management**: Controlling and tracking AI spending across teams
135+
- **Access Control**: Managing which teams can use specific models
136+
- **Usage Analytics**: Understanding how AI is being used across the organization
137+
- **Security & Compliance**: Maintaining enterprise security standards
138+
- **Reliability**: Ensuring consistent service across all users
139+
140+
Portkey adds a comprehensive governance layer to address these enterprise needs. Let's implement these controls step by step.
141+
142+
**Enterprise Implementation Guide**
143+
144+
<AccordionGroup>
145+
<Accordion title="Step 1: Implement Budget Controls & Rate Limits">
146+
### Step 1: Implement Budget Controls & Rate Limits
147+
148+
Virtual Keys enable granular control over LLM access at the team/department level. This helps you:
149+
- Set up [budget limits](/product/ai-gateway/virtual-keys/budget-limits)
150+
- Prevent unexpected usage spikes using Rate limits
151+
- Track departmental spending
152+
153+
#### Setting Up Department-Specific Controls:
154+
1. Navigate to [Virtual Keys](https://app.portkey.ai/virtual-keys) in Portkey dashboard
155+
2. Create new Virtual Key for each department with budget limits and rate limits
156+
3. Configure department-specific limits
157+
158+
<Frame>
159+
<img src="/images/integrations/openai/virtual-key-2.png" width="500"/>
160+
</Frame>
161+
162+
</Accordion>
163+
164+
<Accordion title="Step 2: Define Model Access Rules">
165+
### Step 2: Define Model Access Rules
166+
167+
As your AI usage scales, controlling which teams can access specific models becomes crucial. Portkey Configs provide this control layer with features like:
168+
169+
#### Access Control Features:
170+
- **Model Restrictions**: Limit access to specific models
171+
- **Data Protection**: Implement guardrails for sensitive data
172+
- **Reliability Controls**: Add fallbacks and retry logic
173+
174+
#### Example Configuration:
175+
Here's a basic configuration to route requests to OpenAI, specifically using GPT-4o:
176+
177+
```json
178+
{
179+
"strategy": {
180+
"mode": "single"
181+
},
182+
"targets": [
183+
{
184+
"virtual_key": "YOUR_OPENAI_VIRTUAL_KEY",
185+
"override_params": {
186+
"model": "gpt-4o"
187+
}
188+
}
189+
]
190+
}
191+
```
192+
193+
Create your config on the [Configs page](https://app.portkey.ai/configs) in your Portkey dashboard. You'll need the config ID for connecting to Codex CLI's setup.
194+
195+
196+
<Note>
197+
Configs can be updated anytime to adjust controls without affecting running applications.
198+
</Note>
199+
</Accordion>
200+
201+
<Accordion title="Step 3: Implement Access Controls">
202+
### Step 3: Implement Access Controls
203+
204+
Create User-specific API keys that automatically:
205+
- Track usage per user/team with the help of virtual keys
206+
- Apply appropriate configs to route requests
207+
- Collect relevant metadata to filter logs
208+
- Enforce access permissions
209+
210+
211+
Create API keys through:
212+
- [Portkey App](https://app.portkey.ai/)
213+
- [API Key Management API](/api-reference/admin-api/control-plane/api-keys/create-api-key)
214+
215+
216+
Example using Python SDK:
217+
```python
218+
from portkey_ai import Portkey
219+
220+
portkey = Portkey(api_key="YOUR_ADMIN_API_KEY")
221+
222+
api_key = portkey.api_keys.create(
223+
name="engineering-team",
224+
type="organisation",
225+
workspace_id="YOUR_WORKSPACE_ID",
226+
defaults={
227+
"config_id": "your-config-id",
228+
"metadata": {
229+
"environment": "production",
230+
"department": "engineering"
231+
}
232+
},
233+
scopes=["logs.view", "configs.read"]
234+
)
235+
```
236+
237+
For detailed key management instructions, see our [API Keys documentation](/api-reference/admin-api/control-plane/api-keys/create-api-key).
238+
</Accordion>
239+
240+
<Accordion title="Step 4: Deploy & Monitor">
241+
### Step 4: Deploy & Monitor
242+
After distributing API keys to your team members, your enterprise-ready Codex CLI setup is ready to go. Each team member can now use their designated API keys with appropriate access levels and budget controls.
243+
Apply your governance setup using the integration steps from earlier sections
244+
Monitor usage in Portkey dashboard:
245+
- Cost tracking by department
246+
- Model usage patterns
247+
- Request volumes
248+
- Error rates
249+
</Accordion>
250+
251+
</AccordionGroup>
252+
253+
<Check>
254+
### Enterprise Features Now Available
255+
**Codex CLI now has:**
256+
257+
- Departmental budget controls
258+
- Model access governance
259+
- Usage tracking & attribution
260+
- Security guardrails
261+
- Reliability features
262+
263+
</Check>
264+
265+
# Portkey Features
266+
Now that you have enterprise-grade Codex CLI setup, let's explore the comprehensive features Portkey provides to ensure secure, efficient, and cost-effective AI operations.
267+
268+
### 1. Comprehensive Metrics
269+
Using Portkey you can track 40+ key metrics including cost, token usage, response time, and performance across all your LLM providers in real time. You can also filter these metrics based on custom metadata that you can set in your configs. Learn more about metadata here.
270+
271+
<Frame>
272+
<img src="/images/integrations/observability.png" width="600"/>
273+
</Frame>
274+
275+
### 2. Advanced Logs
276+
Portkey's logging dashboard provides detailed logs for every request made to your LLMs. These logs include:
277+
- Complete request and response tracking
278+
- Metadata tags for filtering
279+
- Cost attribution and much more...
280+
281+
<Frame>
282+
<img src="/images/llms/openai/logs.png"></img>
283+
</Frame>
284+
285+
286+
287+
288+
### 3. Unified Access to 250+ LLMs
289+
290+
You can easily switch between 250+ LLMs. Call various LLMs such as Anthropic, Gemini, Mistral, Azure OpenAI, Google Vertex AI, AWS Bedrock, and many more by simply changing the `virtual_key` in your default `config` object.
291+
292+
293+
### 4. Advanced Metadata Tracking
294+
Using Portkey, you can add custom metadata to your LLM requests for detailed tracking and analytics. Use metadata tags to filter logs, track usage, and attribute costs across departments and teams.
295+
296+
<Card title="Custom Metadata" icon="coins" href="/docs/product/ai-gateway/metadata">
297+
</Card>
298+
299+
300+
301+
### 5. Enterprise Access Management
302+
303+
<CardGroup cols={2}>
304+
<Card title="Budget Controls" icon="coins" href="/docs/product/ai-gateway/virtual-keys/budget-limits">
305+
Set and manage spending limits across teams and departments. Control costs with granular budget limits and usage tracking.
306+
</Card>
307+
308+
<Card title="Single Sign-On (SSO)" icon="key" href="/docs/product/enterprise-offering/org-management/sso">
309+
Enterprise-grade SSO integration with support for SAML 2.0, Okta, Azure AD, and custom providers for secure authentication.
310+
</Card>
311+
312+
<Card title="Organization Management" icon="building" href="/docs/product/enterprise-offering/org-management">
313+
Hierarchical organization structure with workspaces, teams, and role-based access control for enterprise-scale deployments.
314+
</Card>
315+
316+
<Card title="Access Rules & Audit Logs" icon="shield-check" href="/docs/product/enterprise-offering/access-control-management#audit-logs">
317+
Comprehensive access control rules and detailed audit logging for security compliance and usage tracking.
318+
</Card>
319+
</CardGroup>
320+
321+
322+
### 6. Reliability Features
323+
<CardGroup cols={3}>
324+
<Card title="Fallbacks" icon="life-ring" href="/product/ai-gateway/fallbacks">
325+
Automatically switch to backup targets if the primary target fails.
326+
</Card>
327+
<Card title="Conditional Routing" icon="route" href="/product/ai-gateway/conditional-routing">
328+
Route requests to different targets based on specified conditions.
329+
</Card>
330+
<Card title="Load Balancing" icon="key" href="/docs/product/ai-gateway/load-balancing">
331+
Distribute requests across multiple targets based on defined weights.
332+
</Card>
333+
<Card title="Caching" icon="database" href="/product/ai-gateway/caching">
334+
Enable caching of responses to improve performance and reduce costs.
335+
</Card>
336+
<Card title="Smart Retries" icon="database" href="/product/ai-gateway/retries">
337+
Automatic retry handling with exponential backoff for failed requests
338+
</Card>
339+
<Card title="Budget Limits" icon="shield-check" href="/product/ai-gateway/virtual-keys/budget-limits">
340+
Set and manage budget limits across teams and departments. Control costs with granular budget limits and usage tracking.
341+
</Card>
342+
</CardGroup>
343+
344+
345+
346+
### 7. Advanced Guardrails
347+
348+
Protect your Codex CLI's data and enhance reliability with real-time checks on LLM inputs and outputs. Leverage guardrails to:
349+
- Prevent sensitive data leaks
350+
- Enforce compliance with organizational policies
351+
- PII detection and masking
352+
- Content filtering
353+
- Custom security rules
354+
- Data compliance checks
355+
356+
<Card title="Guardrails" icon="shield-check" href="/docs/product/guardrails">
357+
Implement real-time protection for your LLM interactions with automatic detection and filtering of sensitive content, PII, and custom security rules. Enable comprehensive data protection while maintaining compliance with organizational policies.
358+
</Card>
359+
360+
# FAQs
361+
<AccordionGroup>
362+
<Accordion title="How do I update my Virtual Key limits after creation?">
363+
You can update your Virtual Key limits at any time from the Portkey dashboard:1. Go to Virtual Keys section2. Click on the Virtual Key you want to modify3. Update the budget or rate limits4. Save your changes
364+
</Accordion>
365+
<Accordion title="Can I use multiple LLM providers with the same API key?">
366+
Yes! You can create multiple Virtual Keys (one for each provider) and attach them to a single config. This config can then be connected to your API key, allowing you to use multiple providers through a single API key.
367+
</Accordion>
368+
<Accordion title="How do I track costs for different teams?">
369+
Portkey provides several ways to track team costs:
370+
- Create separate Virtual Keys for each team
371+
- Use metadata tags in your configs
372+
- Set up team-specific API keys
373+
- Monitor usage in the analytics dashboard
374+
</Accordion>
375+
<Accordion title="What happens if a team exceeds their budget limit?">
376+
When a team reaches their budget limit:
377+
1. Further requests will be blocked
378+
2. Team admins receive notifications
379+
3. Usage statistics remain available in dashboard
380+
4. Limits can be adjusted if needed
381+
</Accordion>
382+
<Accordion title="Can I use Portkey with the open source version of Codex CLI?">
383+
Yes! Portkey fully integrates with [OpenAI's open source Codex CLI](https://github.com/openai/codex). This gives you the flexibility to leverage both the power of open source with the enterprise controls of Portkey.
384+
</Accordion>
385+
</AccordionGroup>
386+
387+
388+
# Next Steps
389+
390+
**Join our Community**
391+
- [Discord Community](https://portkey.sh/discord-report)
392+
- [GitHub Repository](https://github.com/Portkey-AI)
393+
394+
<Note>
395+
For enterprise support and custom features, contact our [enterprise team](https://calendly.com/portkey-ai).
396+
</Note>

0 commit comments

Comments
 (0)