forked from phoenix/litellm-mirror
Merge pull request #4030 from BerriAI/litellm_audit_logs_premium
[Feat] Audit Logs for Key, User, ProxyModel CRUD operations
This commit is contained in:
Ishaan Jaff
GitHub
commit
8e8509d848
9 changed files with 478 additions and 188 deletions
|
|
@ -10,6 +10,7 @@ For companies that need SSO, user management and professional support for LiteLL
|
|||
This covers:
|
||||
- ✅ **Features under the [LiteLLM Commercial License (Content Mod, Custom Tags, etc.)](https://docs.litellm.ai/docs/proxy/enterprise)**
|
||||
- ✅ [**Secure UI access with Single Sign-On**](../docs/proxy/ui.md#setup-ssoauth-for-ui)
|
||||
- ✅ [**Audit Logs with retention policy**](../docs/proxy/enterprise.md#audit-logs)
|
||||
- ✅ [**JWT-Auth**](../docs/proxy/token_auth.md)
|
||||
- ✅ [**Prompt Injection Detection**](#prompt-injection-detection-lakeraai)
|
||||
- ✅ [**Invite Team Members to access `/spend` Routes**](../docs/proxy/cost_tracking#allowing-non-proxy-admins-to-access-spend-endpoints)
|
||||
|
|
|
|||
|
|
@ -2,30 +2,213 @@ import Image from '@theme/IdealImage';
|
|||
import Tabs from '@theme/Tabs';
|
||||
import TabItem from '@theme/TabItem';
|
||||
|
||||
# ✨ Enterprise Features - Content Mod, SSO, Custom Swagger
|
||||
# ✨ Enterprise Features - SSO, Audit Logs, Guardrails
|
||||
|
||||
Features here are behind a commercial license in our `/enterprise` folder. [**See Code**](https://github.com/BerriAI/litellm/tree/main/enterprise)
|
||||
:::tip
|
||||
|
||||
:::info
|
||||
|
||||
[Get Started with Enterprise here](https://github.com/BerriAI/litellm/tree/main/enterprise)
|
||||
Get in touch with us [here](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)
|
||||
|
||||
:::
|
||||
|
||||
Features:
|
||||
- ✅ [SSO for Admin UI](./ui.md#✨-enterprise-features)
|
||||
- ✅ Content Moderation with LLM Guard, LlamaGuard, Google Text Moderations
|
||||
- ✅ [Prompt Injection Detection (with LakeraAI API)](#prompt-injection-detection-lakeraai)
|
||||
- ✅ [Audit Logs](#audit-logs)
|
||||
- ✅ [Tracking Spend for Custom Tags](#tracking-spend-for-custom-tags)
|
||||
- ✅ [Content Moderation with LLM Guard, LlamaGuard, Google Text Moderations](#content-moderation)
|
||||
- ✅ [Prompt Injection Detection (with LakeraAI API)](#prompt-injection-detection---lakeraai)
|
||||
- ✅ [Custom Branding + Routes on Swagger Docs](#swagger-docs---custom-routes--branding)
|
||||
- ✅ Reject calls from Blocked User list
|
||||
- ✅ Reject calls (incoming / outgoing) with Banned Keywords (e.g. competitors)
|
||||
- ✅ Don't log/store specific requests to Langfuse, Sentry, etc. (eg confidential LLM requests)
|
||||
- ✅ Tracking Spend for Custom Tags
|
||||
- ✅ Custom Branding + Routes on Swagger Docs
|
||||
- ✅ Audit Logs for `Created At, Created By` when Models Added
|
||||
|
||||
## Audit Logs
|
||||
|
||||
Store Audit logs for **Create, Update Delete Operations** done on `Teams` and `Virtual Keys`
|
||||
|
||||
**Step 1** Switch on audit Logs
|
||||
```shell
|
||||
litellm_settings:
|
||||
store_audit_logs: true
|
||||
```
|
||||
|
||||
Start the litellm proxy with this config
|
||||
|
||||
**Step 2** Test it - Create a Team
|
||||
|
||||
```shell
|
||||
curl --location 'http://0.0.0.0:4000/team/new' \
|
||||
--header 'Authorization: Bearer sk-1234' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"max_budget": 2
|
||||
}'
|
||||
```
|
||||
|
||||
**Step 3** Expected Log
|
||||
|
||||
```json
|
||||
{
|
||||
"id": "e1760e10-4264-4499-82cd-c08c86c8d05b",
|
||||
"updated_at": "2024-06-06T02:10:40.836420+00:00",
|
||||
"changed_by": "109010464461339474872",
|
||||
"action": "created",
|
||||
"table_name": "LiteLLM_TeamTable",
|
||||
"object_id": "82e725b5-053f-459d-9a52-867191635446",
|
||||
"before_value": null,
|
||||
"updated_values": {
|
||||
"team_id": "82e725b5-053f-459d-9a52-867191635446",
|
||||
"admins": [],
|
||||
"members": [],
|
||||
"members_with_roles": [
|
||||
{
|
||||
"role": "admin",
|
||||
"user_id": "109010464461339474872"
|
||||
}
|
||||
],
|
||||
"max_budget": 2.0,
|
||||
"models": [],
|
||||
"blocked": false
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
|
||||
## Tracking Spend for Custom Tags
|
||||
|
||||
Requirements:
|
||||
|
||||
- Virtual Keys & a database should be set up, see [virtual keys](https://docs.litellm.ai/docs/proxy/virtual_keys)
|
||||
|
||||
#### Usage - /chat/completions requests with request tags
|
||||
|
||||
|
||||
<Tabs>
|
||||
|
||||
|
||||
<TabItem value="openai" label="OpenAI Python v1.0.0+">
|
||||
|
||||
Set `extra_body={"metadata": { }}` to `metadata` you want to pass
|
||||
|
||||
```python
|
||||
import openai
|
||||
client = openai.OpenAI(
|
||||
api_key="anything",
|
||||
base_url="http://0.0.0.0:4000"
|
||||
)
|
||||
|
||||
# request sent to model set on litellm proxy, `litellm --model`
|
||||
response = client.chat.completions.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "this is a test request, write a short poem"
|
||||
}
|
||||
],
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
print(response)
|
||||
```
|
||||
</TabItem>
|
||||
|
||||
<TabItem value="Curl" label="Curl Request">
|
||||
|
||||
Pass `metadata` as part of the request body
|
||||
|
||||
```shell
|
||||
curl --location 'http://0.0.0.0:4000/chat/completions' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "what llm are you"
|
||||
}
|
||||
],
|
||||
"metadata": {"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]}
|
||||
}'
|
||||
```
|
||||
</TabItem>
|
||||
<TabItem value="langchain" label="Langchain">
|
||||
|
||||
```python
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.prompts.chat import (
|
||||
ChatPromptTemplate,
|
||||
HumanMessagePromptTemplate,
|
||||
SystemMessagePromptTemplate,
|
||||
)
|
||||
from langchain.schema import HumanMessage, SystemMessage
|
||||
|
||||
chat = ChatOpenAI(
|
||||
openai_api_base="http://0.0.0.0:4000",
|
||||
model = "gpt-3.5-turbo",
|
||||
temperature=0.1,
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
messages = [
|
||||
SystemMessage(
|
||||
content="You are a helpful assistant that im using to make a test request to."
|
||||
),
|
||||
HumanMessage(
|
||||
content="test from litellm. tell me why it's amazing in 1 sentence"
|
||||
),
|
||||
]
|
||||
response = chat(messages)
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
|
||||
#### Viewing Spend per tag
|
||||
|
||||
#### `/spend/tags` Request Format
|
||||
```shell
|
||||
curl -X GET "http://0.0.0.0:4000/spend/tags" \
|
||||
-H "Authorization: Bearer sk-1234"
|
||||
```
|
||||
|
||||
#### `/spend/tags`Response Format
|
||||
```shell
|
||||
[
|
||||
{
|
||||
"individual_request_tag": "model-anthropic-claude-v2.1",
|
||||
"log_count": 6,
|
||||
"total_spend": 0.000672
|
||||
},
|
||||
{
|
||||
"individual_request_tag": "app-ishaan-local",
|
||||
"log_count": 4,
|
||||
"total_spend": 0.000448
|
||||
},
|
||||
{
|
||||
"individual_request_tag": "app-ishaan-prod",
|
||||
"log_count": 2,
|
||||
"total_spend": 0.000224
|
||||
}
|
||||
]
|
||||
|
||||
```
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
## Content Moderation
|
||||
### Content Moderation with LLM Guard
|
||||
#### Content Moderation with LLM Guard
|
||||
|
||||
Set the LLM Guard API Base in your environment
|
||||
|
||||
|
|
@ -160,7 +343,7 @@ curl --location 'http://0.0.0.0:4000/v1/chat/completions' \
|
|||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
### Content Moderation with LlamaGuard
|
||||
#### Content Moderation with LlamaGuard
|
||||
|
||||
Currently works with Sagemaker's LlamaGuard endpoint.
|
||||
|
||||
|
|
@ -194,7 +377,7 @@ callbacks: ["llamaguard_moderations"]
|
|||
|
||||
|
||||
|
||||
### Content Moderation with Google Text Moderation
|
||||
#### Content Moderation with Google Text Moderation
|
||||
|
||||
Requires your GOOGLE_APPLICATION_CREDENTIALS to be set in your .env (same as VertexAI).
|
||||
|
||||
|
|
@ -250,7 +433,7 @@ Here are the category specific values:
|
|||
|
||||
|
||||
|
||||
### Content Moderation with OpenAI Moderations
|
||||
#### Content Moderation with OpenAI Moderations
|
||||
|
||||
Use this if you want to reject /chat, /completions, /embeddings calls that fail OpenAI Moderations checks
|
||||
|
||||
|
|
@ -302,6 +485,42 @@ curl --location 'http://localhost:4000/chat/completions' \
|
|||
}'
|
||||
```
|
||||
|
||||
## Swagger Docs - Custom Routes + Branding
|
||||
|
||||
:::info
|
||||
|
||||
Requires a LiteLLM Enterprise key to use. Get a free 2-week license [here](https://forms.gle/sTDVprBs18M4V8Le8)
|
||||
|
||||
:::
|
||||
|
||||
Set LiteLLM Key in your environment
|
||||
|
||||
```bash
|
||||
LITELLM_LICENSE=""
|
||||
```
|
||||
|
||||
#### Customize Title + Description
|
||||
|
||||
In your environment, set:
|
||||
|
||||
```bash
|
||||
DOCS_TITLE="TotalGPT"
|
||||
DOCS_DESCRIPTION="Sample Company Description"
|
||||
```
|
||||
|
||||
#### Customize Routes
|
||||
|
||||
Hide admin routes from users.
|
||||
|
||||
In your environment, set:
|
||||
|
||||
```bash
|
||||
DOCS_FILTERED="True" # only shows openai routes to user
|
||||
```
|
||||
|
||||
<Image img={require('../../img/custom_swagger.png')} style={{ width: '900px', height: 'auto' }} />
|
||||
|
||||
|
||||
## Enable Blocked User Lists
|
||||
If any call is made to proxy with this user id, it'll be rejected - use this if you want to let users opt-out of ai features
|
||||
|
||||
|
|
@ -417,176 +636,6 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
|
|||
}
|
||||
'
|
||||
```
|
||||
## Tracking Spend for Custom Tags
|
||||
|
||||
Requirements:
|
||||
|
||||
- Virtual Keys & a database should be set up, see [virtual keys](https://docs.litellm.ai/docs/proxy/virtual_keys)
|
||||
|
||||
### Usage - /chat/completions requests with request tags
|
||||
|
||||
|
||||
<Tabs>
|
||||
|
||||
|
||||
<TabItem value="openai" label="OpenAI Python v1.0.0+">
|
||||
|
||||
Set `extra_body={"metadata": { }}` to `metadata` you want to pass
|
||||
|
||||
```python
|
||||
import openai
|
||||
client = openai.OpenAI(
|
||||
api_key="anything",
|
||||
base_url="http://0.0.0.0:4000"
|
||||
)
|
||||
|
||||
# request sent to model set on litellm proxy, `litellm --model`
|
||||
response = client.chat.completions.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "this is a test request, write a short poem"
|
||||
}
|
||||
],
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
print(response)
|
||||
```
|
||||
</TabItem>
|
||||
|
||||
<TabItem value="Curl" label="Curl Request">
|
||||
|
||||
Pass `metadata` as part of the request body
|
||||
|
||||
```shell
|
||||
curl --location 'http://0.0.0.0:4000/chat/completions' \
|
||||
--header 'Content-Type: application/json' \
|
||||
--data '{
|
||||
"model": "gpt-3.5-turbo",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "what llm are you"
|
||||
}
|
||||
],
|
||||
"metadata": {"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]}
|
||||
}'
|
||||
```
|
||||
</TabItem>
|
||||
<TabItem value="langchain" label="Langchain">
|
||||
|
||||
```python
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.prompts.chat import (
|
||||
ChatPromptTemplate,
|
||||
HumanMessagePromptTemplate,
|
||||
SystemMessagePromptTemplate,
|
||||
)
|
||||
from langchain.schema import HumanMessage, SystemMessage
|
||||
|
||||
chat = ChatOpenAI(
|
||||
openai_api_base="http://0.0.0.0:4000",
|
||||
model = "gpt-3.5-turbo",
|
||||
temperature=0.1,
|
||||
extra_body={
|
||||
"metadata": {
|
||||
"tags": ["model-anthropic-claude-v2.1", "app-ishaan-prod"]
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
messages = [
|
||||
SystemMessage(
|
||||
content="You are a helpful assistant that im using to make a test request to."
|
||||
),
|
||||
HumanMessage(
|
||||
content="test from litellm. tell me why it's amazing in 1 sentence"
|
||||
),
|
||||
]
|
||||
response = chat(messages)
|
||||
|
||||
print(response)
|
||||
```
|
||||
|
||||
</TabItem>
|
||||
</Tabs>
|
||||
|
||||
|
||||
### Viewing Spend per tag
|
||||
|
||||
#### `/spend/tags` Request Format
|
||||
```shell
|
||||
curl -X GET "http://0.0.0.0:4000/spend/tags" \
|
||||
-H "Authorization: Bearer sk-1234"
|
||||
```
|
||||
|
||||
#### `/spend/tags`Response Format
|
||||
```shell
|
||||
[
|
||||
{
|
||||
"individual_request_tag": "model-anthropic-claude-v2.1",
|
||||
"log_count": 6,
|
||||
"total_spend": 0.000672
|
||||
},
|
||||
{
|
||||
"individual_request_tag": "app-ishaan-local",
|
||||
"log_count": 4,
|
||||
"total_spend": 0.000448
|
||||
},
|
||||
{
|
||||
"individual_request_tag": "app-ishaan-prod",
|
||||
"log_count": 2,
|
||||
"total_spend": 0.000224
|
||||
}
|
||||
]
|
||||
|
||||
```
|
||||
|
||||
|
||||
<!-- ## Tracking Spend per Key
|
||||
|
||||
## Tracking Spend per User -->
|
||||
|
||||
## Swagger Docs - Custom Routes + Branding
|
||||
|
||||
:::info
|
||||
|
||||
Requires a LiteLLM Enterprise key to use. Get a free 2-week license [here](https://forms.gle/sTDVprBs18M4V8Le8)
|
||||
|
||||
:::
|
||||
|
||||
Set LiteLLM Key in your environment
|
||||
|
||||
```bash
|
||||
LITELLM_LICENSE=""
|
||||
```
|
||||
|
||||
### Customize Title + Description
|
||||
|
||||
In your environment, set:
|
||||
|
||||
```bash
|
||||
DOCS_TITLE="TotalGPT"
|
||||
DOCS_DESCRIPTION="Sample Company Description"
|
||||
```
|
||||
|
||||
### Customize Routes
|
||||
|
||||
Hide admin routes from users.
|
||||
|
||||
In your environment, set:
|
||||
|
||||
```bash
|
||||
DOCS_FILTERED="True" # only shows openai routes to user
|
||||
```
|
||||
|
||||
<Image img={require('../../img/custom_swagger.png')} style={{ width: '900px', height: 'auto' }} />
|
||||
|
||||
## Public Model Hub
|
||||
|
||||
|
|
|
|||
|
|
@ -36,6 +36,7 @@ const sidebars = {
|
|||
label: "📖 All Endpoints (Swagger)",
|
||||
href: "https://litellm-api.up.railway.app/",
|
||||
},
|
||||
"proxy/enterprise",
|
||||
"proxy/demo",
|
||||
"proxy/configs",
|
||||
"proxy/reliability",
|
||||
|
|
@ -45,7 +46,6 @@ const sidebars = {
|
|||
"proxy/customers",
|
||||
"proxy/billing",
|
||||
"proxy/user_keys",
|
||||
"proxy/enterprise",
|
||||
"proxy/virtual_keys",
|
||||
"proxy/alerting",
|
||||
{
|
||||
|
|
|
|||
|
|
@ -60,6 +60,7 @@ _async_failure_callback: List[Callable] = (
|
|||
pre_call_rules: List[Callable] = []
|
||||
post_call_rules: List[Callable] = []
|
||||
turn_off_message_logging: Optional[bool] = False
|
||||
store_audit_logs = False # Enterprise feature, allow users to see audit logs
|
||||
## end of callbacks #############
|
||||
|
||||
email: Optional[str] = (
|
||||
|
|
|
|||
|
|
@ -76,6 +76,17 @@ class LitellmUserRoles(str, enum.Enum):
|
|||
return ui_labels.get(self.value, "")
|
||||
|
||||
|
||||
class LitellmTableNames(str, enum.Enum):
|
||||
"""
|
||||
Enum for Table Names used by LiteLLM
|
||||
"""
|
||||
|
||||
TEAM_TABLE_NAME: str = "LiteLLM_TeamTable"
|
||||
USER_TABLE_NAME: str = "LiteLLM_UserTable"
|
||||
KEY_TABLE_NAME: str = "LiteLLM_VerificationToken"
|
||||
PROXY_MODEL_TABLE_NAME: str = "LiteLLM_ModelTable"
|
||||
|
||||
|
||||
AlertType = Literal[
|
||||
"llm_exceptions",
|
||||
"llm_too_slow",
|
||||
|
|
@ -1276,6 +1287,22 @@ class LiteLLM_ErrorLogs(LiteLLMBase):
|
|||
endTime: Union[str, datetime, None]
|
||||
|
||||
|
||||
class LiteLLM_AuditLogs(LiteLLMBase):
|
||||
id: str
|
||||
updated_at: datetime
|
||||
changed_by: str
|
||||
action: Literal["created", "updated", "deleted"]
|
||||
table_name: Literal[
|
||||
LitellmTableNames.TEAM_TABLE_NAME,
|
||||
LitellmTableNames.USER_TABLE_NAME,
|
||||
LitellmTableNames.KEY_TABLE_NAME,
|
||||
LitellmTableNames.PROXY_MODEL_TABLE_NAME,
|
||||
]
|
||||
object_id: str
|
||||
before_value: Optional[Json] = None
|
||||
updated_values: Optional[Json] = None
|
||||
|
||||
|
||||
class LiteLLM_SpendLogs_ResponseObject(LiteLLMBase):
|
||||
response: Optional[List[Union[LiteLLM_SpendLogs, Any]]] = None
|
||||
|
||||
|
|
|
|||
|
|
@ -24,3 +24,4 @@ general_settings:
|
|||
|
||||
litellm_settings:
|
||||
callbacks: ["otel"]
|
||||
store_audit_logs: true
|
||||
|
|
@ -7115,6 +7115,25 @@ async def generate_key_fn(
|
|||
)
|
||||
)
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
if litellm.store_audit_logs is True:
|
||||
_updated_values = json.dumps(response)
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id
|
||||
or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.KEY_TABLE_NAME,
|
||||
object_id=response.get("token_id", ""),
|
||||
action="created",
|
||||
updated_values=_updated_values,
|
||||
before_value=None,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
return GenerateKeyResponse(**response)
|
||||
except Exception as e:
|
||||
traceback.print_exc()
|
||||
|
|
@ -7138,7 +7157,11 @@ async def generate_key_fn(
|
|||
@router.post(
|
||||
"/key/update", tags=["key management"], dependencies=[Depends(user_api_key_auth)]
|
||||
)
|
||||
async def update_key_fn(request: Request, data: UpdateKeyRequest):
|
||||
async def update_key_fn(
|
||||
request: Request,
|
||||
data: UpdateKeyRequest,
|
||||
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
|
||||
):
|
||||
"""
|
||||
Update an existing key
|
||||
"""
|
||||
|
|
@ -7150,6 +7173,16 @@ async def update_key_fn(request: Request, data: UpdateKeyRequest):
|
|||
if prisma_client is None:
|
||||
raise Exception("Not connected to DB!")
|
||||
|
||||
existing_key_row = await prisma_client.get_data(
|
||||
token=data.key, table_name="key", query_type="find_unique"
|
||||
)
|
||||
|
||||
if existing_key_row is None:
|
||||
raise HTTPException(
|
||||
status_code=404,
|
||||
detail={"error": f"Team not found, passed team_id={data.team_id}"},
|
||||
)
|
||||
|
||||
# get non default values for key
|
||||
non_default_values = {}
|
||||
for k, v in data_json.items():
|
||||
|
|
@ -7176,6 +7209,29 @@ async def update_key_fn(request: Request, data: UpdateKeyRequest):
|
|||
hashed_token = hash_token(key)
|
||||
user_api_key_cache.delete_cache(hashed_token)
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
if litellm.store_audit_logs is True:
|
||||
_updated_values = json.dumps(data_json)
|
||||
|
||||
_before_value = existing_key_row.json(exclude_none=True)
|
||||
_before_value = json.dumps(_before_value)
|
||||
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id
|
||||
or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.KEY_TABLE_NAME,
|
||||
object_id=data.key,
|
||||
action="updated",
|
||||
updated_values=_updated_values,
|
||||
before_value=_before_value,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
return {"key": key, **response["data"]}
|
||||
# update based on remaining passed in values
|
||||
except Exception as e:
|
||||
|
|
@ -7238,6 +7294,34 @@ async def delete_key_fn(
|
|||
):
|
||||
user_id = None # unless they're admin
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
# we do this after the first for loop, since first for loop is for validation. we only want this inserted after validation passes
|
||||
if litellm.store_audit_logs is True:
|
||||
# make an audit log for each team deleted
|
||||
for key in data.keys:
|
||||
key_row = await prisma_client.get_data( # type: ignore
|
||||
token=key, table_name="key", query_type="find_unique"
|
||||
)
|
||||
|
||||
key_row = key_row.json(exclude_none=True)
|
||||
_key_row = json.dumps(key_row)
|
||||
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id
|
||||
or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.KEY_TABLE_NAME,
|
||||
object_id=key,
|
||||
action="deleted",
|
||||
updated_values="{}",
|
||||
before_value=_key_row,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
number_deleted_keys = await delete_verification_token(
|
||||
tokens=keys, user_id=user_id
|
||||
)
|
||||
|
|
@ -10365,12 +10449,65 @@ async def new_team(
|
|||
}
|
||||
},
|
||||
)
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
if litellm.store_audit_logs is True:
|
||||
_updated_values = complete_team_data.json(exclude_none=True)
|
||||
_updated_values = json.dumps(_updated_values)
|
||||
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.TEAM_TABLE_NAME,
|
||||
object_id=data.team_id,
|
||||
action="created",
|
||||
updated_values=_updated_values,
|
||||
before_value=None,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
try:
|
||||
return team_row.model_dump()
|
||||
except Exception as e:
|
||||
return team_row.dict()
|
||||
|
||||
|
||||
async def create_audit_log_for_update(request_data: LiteLLM_AuditLogs):
|
||||
if premium_user is not True:
|
||||
return
|
||||
|
||||
if litellm.store_audit_logs is not True:
|
||||
return
|
||||
if prisma_client is None:
|
||||
raise Exception("prisma_client is None, no DB connected")
|
||||
|
||||
verbose_proxy_logger.debug("creating audit log for %s", request_data)
|
||||
|
||||
if isinstance(request_data.updated_values, dict):
|
||||
request_data.updated_values = json.dumps(request_data.updated_values)
|
||||
|
||||
if isinstance(request_data.before_value, dict):
|
||||
request_data.before_value = json.dumps(request_data.before_value)
|
||||
|
||||
_request_data = request_data.dict(exclude_none=True)
|
||||
|
||||
try:
|
||||
await prisma_client.db.litellm_auditlog.create(
|
||||
data={
|
||||
**_request_data, # type: ignore
|
||||
}
|
||||
)
|
||||
except Exception as e:
|
||||
# [Non-Blocking Exception. Do not allow blocking LLM API call]
|
||||
verbose_proxy_logger.error(f"Failed Creating audit log {e}")
|
||||
|
||||
return
|
||||
|
||||
|
||||
@router.post(
|
||||
"/team/update", tags=["team management"], dependencies=[Depends(user_api_key_auth)]
|
||||
)
|
||||
|
|
@ -10443,6 +10580,27 @@ async def update_team(
|
|||
team_id=data.team_id,
|
||||
)
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
if litellm.store_audit_logs is True:
|
||||
_before_value = existing_team_row.json(exclude_none=True)
|
||||
_before_value = json.dumps(_before_value)
|
||||
_after_value: str = json.dumps(updated_kv)
|
||||
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.TEAM_TABLE_NAME,
|
||||
object_id=data.team_id,
|
||||
action="updated",
|
||||
updated_values=_after_value,
|
||||
before_value=_before_value,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
return team_row
|
||||
|
||||
|
||||
|
|
@ -10714,6 +10872,35 @@ async def delete_team(
|
|||
detail={"error": f"Team not found, passed team_id={team_id}"},
|
||||
)
|
||||
|
||||
# Enterprise Feature - Audit Logging. Enable with litellm.store_audit_logs = True
|
||||
# we do this after the first for loop, since first for loop is for validation. we only want this inserted after validation passes
|
||||
if litellm.store_audit_logs is True:
|
||||
# make an audit log for each team deleted
|
||||
for team_id in data.team_ids:
|
||||
team_row = await prisma_client.get_data( # type: ignore
|
||||
team_id=team_id, table_name="team", query_type="find_unique"
|
||||
)
|
||||
|
||||
_team_row = team_row.json(exclude_none=True)
|
||||
|
||||
asyncio.create_task(
|
||||
create_audit_log_for_update(
|
||||
request_data=LiteLLM_AuditLogs(
|
||||
id=str(uuid.uuid4()),
|
||||
updated_at=datetime.now(timezone.utc),
|
||||
changed_by=user_api_key_dict.user_id
|
||||
or litellm_proxy_admin_name,
|
||||
table_name=LitellmTableNames.TEAM_TABLE_NAME,
|
||||
object_id=team_id,
|
||||
action="deleted",
|
||||
updated_values="{}",
|
||||
before_value=_team_row,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
# End of Audit logging
|
||||
|
||||
## DELETE ASSOCIATED KEYS
|
||||
await prisma_client.delete_data(team_id_list=data.team_ids, table_name="key")
|
||||
## DELETE TEAMS
|
||||
|
|
|
|||
|
|
@ -244,3 +244,15 @@ model LiteLLM_InvitationLink {
|
|||
liteLLM_user_table_created LiteLLM_UserTable @relation("CreatedBy", fields: [created_by], references: [user_id])
|
||||
liteLLM_user_table_updated LiteLLM_UserTable @relation("UpdatedBy", fields: [updated_by], references: [user_id])
|
||||
}
|
||||
|
||||
|
||||
model LiteLLM_AuditLog {
|
||||
id String @id @default(uuid())
|
||||
updated_at DateTime @default(now())
|
||||
changed_by String // user or system that performed the action
|
||||
action String // create, update, delete
|
||||
table_name String // on of LitellmTableNames.TEAM_TABLE_NAME, LitellmTableNames.USER_TABLE_NAME, LitellmTableNames.PROXY_MODEL_TABLE_NAME,
|
||||
object_id String // id of the object being audited. This can be the key id, team id, user id, model id
|
||||
before_value Json? // value of the row
|
||||
updated_values Json? // value of the row after change
|
||||
}
|
||||
|
|
@ -244,3 +244,15 @@ model LiteLLM_InvitationLink {
|
|||
liteLLM_user_table_created LiteLLM_UserTable @relation("CreatedBy", fields: [created_by], references: [user_id])
|
||||
liteLLM_user_table_updated LiteLLM_UserTable @relation("UpdatedBy", fields: [updated_by], references: [user_id])
|
||||
}
|
||||
|
||||
|
||||
model LiteLLM_AuditLog {
|
||||
id String @id @default(uuid())
|
||||
updated_at DateTime @default(now())
|
||||
changed_by String // user or system that performed the action
|
||||
action String // create, update, delete
|
||||
table_name String // on of LitellmTableNames.TEAM_TABLE_NAME, LitellmTableNames.USER_TABLE_NAME, LitellmTableNames.PROXY_MODEL_TABLE_NAME,
|
||||
object_id String // id of the object being audited. This can be the key id, team id, user id, model id
|
||||
before_value Json? // value of the row
|
||||
updated_values Json? // value of the row after change
|
||||
}
|
||||
Loading…
Add table
Add a link
Reference in a new issue