mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-07 02:59:05 +00:00
docs: fix duplicate word typos across documentation
Fix 6 instances of duplicate words ("the the", "for for", "with with",
"to to") in proxy, providers, and guides documentation pages.
Files fixed:
- proxy/prod.md: "the the" -> "the"
- proxy/architecture.md: "the the" -> "the"
- guides/security_settings.md: "the the" -> "the"
- proxy/prometheus.md: "for for" -> "for"
- proxy/cost_tracking.md: "with with" -> "with"
- providers/lemonade.md: "to to" -> "to"
This commit is contained in:
parent
e5baa2232f
commit
cde25180a3
6 changed files with 6 additions and 6 deletions
|
|
@ -13,7 +13,7 @@ LiteLLM uses HTTPX for network requests, unless otherwise specified.
|
|||
|
||||
## 1. Custom CA Bundle
|
||||
|
||||
You can set a custom CA bundle file path using the `SSL_CERT_FILE` environmental variable or passing a string to the the ssl_verify setting.
|
||||
You can set a custom CA bundle file path using the `SSL_CERT_FILE` environmental variable or passing a string to the ssl_verify setting.
|
||||
|
||||
<Tabs>
|
||||
<TabItem value="sdk" label="SDK">
|
||||
|
|
|
|||
|
|
@ -185,7 +185,7 @@ print("Available models:", [model['id'] for model in models.get('data', [])])
|
|||
|
||||
## Support
|
||||
|
||||
For more information regarding Lemonade please go to to the [Lemonade website](https://lemonade-server.ai/) or [Lemonade repository](https://github.com/lemonade-sdk/lemonade).
|
||||
For more information regarding Lemonade please go to the [Lemonade website](https://lemonade-server.ai/) or [Lemonade repository](https://github.com/lemonade-sdk/lemonade).
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ import TabItem from '@theme/TabItem';
|
|||
- 2.1 Check if the Virtual Key exists in Redis Cache or In Memory Cache
|
||||
- 2.2 **If not in Cache**, Lookup Virtual Key in DB
|
||||
|
||||
3. **Rate Limiting**: The [MaxParallelRequestsHandler](https://github.com/BerriAI/litellm/blob/main/litellm/proxy/hooks/parallel_request_limiter.py) checks the **rate limit (rpm/tpm)** for the the following components:
|
||||
3. **Rate Limiting**: The [MaxParallelRequestsHandler](https://github.com/BerriAI/litellm/blob/main/litellm/proxy/hooks/parallel_request_limiter.py) checks the **rate limit (rpm/tpm)** for the following components:
|
||||
- Global Server Rate Limit
|
||||
- Virtual Key Rate Limit
|
||||
- User Rate Limit
|
||||
|
|
|
|||
|
|
@ -169,7 +169,7 @@ Schedule a [meeting with us to get your Enterprise License](https://calendly.com
|
|||
|
||||
##### Create Key
|
||||
|
||||
Create Key with with `permissions={"get_spend_routes": true}`
|
||||
Create Key with `permissions={"get_spend_routes": true}`
|
||||
|
||||
```shell title="Generate Key with Spend Route Permissions" showLineNumbers
|
||||
curl --location 'http://0.0.0.0:4000/key/generate' \
|
||||
|
|
|
|||
|
|
@ -380,7 +380,7 @@ The proxy will log a warning about the UI but API endpoints will work normally.
|
|||
|
||||
## 10. Use a Separate Health Check App
|
||||
:::info
|
||||
The Separate Health Check App only runs when running via the the LiteLLM Docker Image and using Docker and setting the SEPARATE_HEALTH_APP env var to "1"
|
||||
The Separate Health Check App only runs when running via the LiteLLM Docker Image and using Docker and setting the SEPARATE_HEALTH_APP env var to "1"
|
||||
:::
|
||||
|
||||
Using a separate health check app ensures that your liveness and readiness probes remain responsive even when the main application is under heavy load.
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ This directory is used by the Prometheus client library to store metric files th
|
|||
|
||||
## Virtual Keys, Teams, Internal Users
|
||||
|
||||
Use this for for tracking per [user, key, team, etc.](virtual_keys)
|
||||
Use this for tracking per [user, key, team, etc.](virtual_keys)
|
||||
|
||||
| Metric Name | Description |
|
||||
|----------------------|--------------------------------------|
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue