Merge branch 'main' of github.com:lunary-ai/litellm

.github/workflows/ghcr_deploy.yml

@@ -147,13 +147,19 @@ jobs:
               core.setFailed(error.message);
             }
       - name: Github Releases To Discord
-        uses: SethCohen/github-releases-to-discord@v1.13.1
+        env:
-        with:
+          WEBHOOK_URL: ${{ secrets.WEBHOOK_URL }}
-          webhook_url: ${{ secrets.WEBHOOK_URL }}
+        run: |
-          color: "2105893"
+          curl -H "Content-Type: application/json" -X POST -d '{
-          username: "Release Changelog"
+            "content": "||@everyone||",
-          avatar_url: "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png"
+            "username": "Release Changelog",
-          content: "||@everyone||"
+            "avatar_url": "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png",
-          footer_title: "Changelog"
+            "embeds": [
-          footer_icon_url: "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png"
+              {
-          footer_timestamp: true
+                "title": "Changelog",
+                "description": "This is the changelog for the latest release.",
+                "color": 2105893
+              }
+            ]
+          }' $WEBHOOK_URL
+

docs/my-website/docs/enterprise.md

@@ -1,15 +1,29 @@
 # Enterprise
-
+For companies that need better security, user management and professional support
-LiteLLM offers dedicated enterprise support.
-
-This covers: 
-- **Feature Prioritization**
-- **Custom Integrations**
-- **Professional Support - Dedicated discord + slack**
-- **Custom SLAs**
 
 :::info
 
 [Talk to founders](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)
 
 :::
+
+This covers: 
+- ✅ **Features under the [LiteLLM Commercial License](https://docs.litellm.ai/docs/proxy/enterprise):**
+- ✅ **Feature Prioritization**
+- ✅ **Custom Integrations**
+- ✅ **Professional Support - Dedicated discord + slack**
+- ✅ **Custom SLAs**
+- ✅ **Secure access with Single Sign-On**
+
+
+## Frequently Asked Questions
+
+### What topics does Professional support cover and what SLAs do you offer?
+
+Professional Support can assist with LLM/Provider integrations, deployment, upgrade management, and LLM Provider troubleshooting.  We can’t solve your own infrastructure-related issues but we will guide you to fix them.
+
+We offer custom SLAs based on your needs and the severity of the issue. The standard SLA is 6 hours for Sev0-Sev1 severity and 24h for Sev2-Sev3 between 7am – 7pm PT (Monday through Saturday).
+
+### What’s the cost of the Self-Managed Enterprise edition?
+
+Self-Managed Enterprise deployments require our team to understand your exact needs. [Get in touch with us to learn more](https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat)

docs/my-website/docs/providers/azure_ai.md

@@ -2,16 +2,36 @@
 
 ## Using Mistral models deployed on Azure AI Studio
 
-**Ensure you have the `/v1` in your api_base**
+### Sample Usage - setting env vars 
+
+Set `MISTRAL_AZURE_API_KEY` and `MISTRAL_AZURE_API_BASE` in your env
+
+```shell
+MISTRAL_AZURE_API_KEY = "zE************""
+MISTRAL_AZURE_API_BASE = "https://Mistral-large-nmefg-serverless.eastus2.inference.ai.azure.com"
+```
 
-### Sample Usage
 ```python
 from litellm import completion
 import os
 
 response = completion(
     model="mistral/Mistral-large-dfgfj", 
-    api_base="https://Mistral-large-dfgfj-serverless.eastus2.inference.ai.azure.com/v1",
+    messages=[
+       {"role": "user", "content": "hello from litellm"}
+   ],
+)
+print(response)
+```
+
+### Sample Usage - passing `api_base` and `api_key` to `litellm.completion`
+```python
+from litellm import completion
+import os
+
+response = completion(
+    model="mistral/Mistral-large-dfgfj", 
+    api_base="https://Mistral-large-dfgfj-serverless.eastus2.inference.ai.azure.com",
     api_key = "JGbKodRcTp****"
     messages=[
        {"role": "user", "content": "hello from litellm"}
@@ -23,14 +43,12 @@ print(response)
 ### [LiteLLM Proxy] Using Mistral Models 
 
 Set this on your litellm proxy config.yaml
-
-**Ensure you have the `/v1` in your api_base**
 ```yaml
 model_list:
   - model_name: mistral
     litellm_params:
       model: mistral/Mistral-large-dfgfj
-      api_base: https://Mistral-large-dfgfj-serverless.eastus2.inference.ai.azure.com/v1
+      api_base: https://Mistral-large-dfgfj-serverless.eastus2.inference.ai.azure.com
       api_key: JGbKodRcTp****
 ```
 

docs/my-website/docs/providers/groq.md

@@ -1,6 +1,8 @@
 # Groq
 https://groq.com/
 
+**We support ALL Groq models, just set `groq/` as a prefix when sending completion requests**
+
 ## API Key
 ```python
 # env variable
@@ -47,3 +49,4 @@ We support ALL Groq models, just set `groq/` as a prefix when sending completion
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` | 
+| mixtral-8x7b-32768 | `completion(model="groq/mixtral-8x7b-32768", messages)` | 

docs/my-website/docs/providers/vertex.md

@@ -152,8 +152,14 @@ LiteLLM Supports the following image types passed in `url`
 - Images with Cloud Storage URIs - gs://cloud-samples-data/generative-ai/image/boats.jpeg
 - Images with direct links - https://storage.googleapis.com/github-repo/img/gemini/intro/landmark3.jpg
 - Videos with Cloud Storage URIs - https://storage.googleapis.com/github-repo/img/gemini/multimodality_usecases_overview/pixel8.mp4
+- Base64 Encoded Local Images
+
+**Example Request - image url**
+
+<Tabs>
+
+<TabItem value="direct" label="Images with direct links">
 
-**Example Request**
 ```python
 import litellm
 
@@ -179,6 +185,43 @@ response = litellm.completion(
 )
 print(response)
 ```
+</TabItem>
+
+<TabItem value="base" label="Local Base64 Images">
+
+```python
+import litellm
+
+def encode_image(image_path):
+    import base64
+
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+image_path = "cached_logo.jpg"
+# Getting the base64 string
+base64_image = encode_image(image_path)
+response = litellm.completion(
+    model="vertex_ai/gemini-pro-vision",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Whats in this image?"},
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "data:image/jpeg;base64," + base64_image
+                    },
+                },
+            ],
+        }
+    ],
+)
+print(response)
+```
+</TabItem>
+</Tabs>
 
 
 ## Chat Models

docs/my-website/docs/proxy/load_balancing.md

@@ -1,4 +1,4 @@
-# Multiple Instances of 1 model
+# Load Balancing - Config Setup
 Load balance multiple instances of the same model
 
 The proxy will handle routing requests (using LiteLLM's Router). **Set `rpm` in the config if you want maximize throughput**
@@ -79,6 +79,32 @@ curl --location 'http://0.0.0.0:8000/chat/completions' \
 '
 ```
 
+## Load Balancing using multiple litellm instances (Kubernetes, Auto Scaling)
+
+LiteLLM Proxy supports sharing rpm/tpm shared across multiple litellm instances, pass `redis_host`, `redis_password` and `redis_port` to enable this. (LiteLLM will use Redis to track rpm/tpm usage )
+
+Example config
+
+```yaml
+model_list:
+  - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: azure/<your-deployment-name>
+      api_base: <your-azure-endpoint>
+      api_key: <your-azure-api-key>
+      rpm: 6      # Rate limit for this deployment: in requests per minute (rpm)
+  - model_name: gpt-3.5-turbo
+    litellm_params:
+      model: azure/gpt-turbo-small-ca
+      api_base: https://my-endpoint-canada-berri992.openai.azure.com/
+      api_key: <your-azure-api-key>
+      rpm: 6
+router_settings:
+  redis_host: <your redis host>
+  redis_password: <your redis password>
+  redis_port: 1992
+```
+
 ## Router settings on config - routing_strategy, model_group_alias
 
 litellm.Router() settings can be set under `router_settings`. You can set `model_group_alias`, `routing_strategy`, `num_retries`,`timeout` . See all Router supported params [here](https://github.com/BerriAI/litellm/blob/1b942568897a48f014fa44618ec3ce54d7570a46/litellm/router.py#L64)
@@ -103,4 +129,7 @@ router_settings:
   routing_strategy: least-busy                  # Literal["simple-shuffle", "least-busy", "usage-based-routing", "latency-based-routing"]
   num_retries: 2
   timeout: 30                                  # 30 seconds
+  redis_host: <your redis host>
+  redis_password: <your redis password>
+  redis_port: 1992
 ```

docs/my-website/docs/proxy/ui.md

@@ -2,7 +2,7 @@ import Image from '@theme/IdealImage';
 import Tabs from '@theme/Tabs';
 import TabItem from '@theme/TabItem';
 
-# 🔑 [BETA] Proxy UI 
+# [BETA] Proxy UI 
 ### **Create + delete keys through a UI**
 
 [Let users create their own keys](#setup-ssoauth-for-ui)

docs/my-website/docs/proxy/virtual_keys.md

@@ -1,4 +1,4 @@
-# Virtual Keys, Users
+# 🔑 Virtual Keys, Users
 Track Spend, Set budgets and create virtual keys for the proxy
 
 Grant other's temporary access to your proxy, with keys that expire after a set duration.
@@ -343,18 +343,83 @@ A key will be generated for the new user created
   "key_name": null,
   "expires": null
 }
-
 ```
 
-Request Params:
+
-- keys: List[str] - List of keys to delete
+## /user/info
+
+### Request
+
+#### View all Users
+If you're trying to view all users, we recommend using pagination with the following args
+- `view_all=true`
+- `page=0` Optional(int) min = 0, default=0
+- `page_size=25` Optional(int) min = 1, default = 25
+```shell
+curl -X GET "http://0.0.0.0:4000/user/info?view_all=true&page=0&page_size=25" -H "Authorization: Bearer sk-1234"
+```
+
+#### View specific user_id
+```shell
+curl -X GET "http://0.0.0.0:4000/user/info?user_id=228da235-eef0-4c30-bf53-5d6ac0d278c2" -H "Authorization: Bearer sk-1234"
+```
 
 ### Response
+View user spend, budget, models, keys and teams 
 
 ```json
 {
-  "deleted_keys": ["sk-kdEXbIqZRwEeEiHwdg7sFA"]
+  "user_id": "228da235-eef0-4c30-bf53-5d6ac0d278c2",
+  "user_info": {
+    "user_id": "228da235-eef0-4c30-bf53-5d6ac0d278c2",
+    "team_id": null,
+    "teams": [],
+    "user_role": "app_user",
+    "max_budget": null,
+    "spend": 200000.0,
+    "user_email": null,
+    "models": [],
+    "max_parallel_requests": null,
+    "tpm_limit": null,
+    "rpm_limit": null,
+    "budget_duration": null,
+    "budget_reset_at": null,
+    "allowed_cache_controls": [],
+    "model_spend": {
+      "chatgpt-v-2": 200000
+    },
+    "model_max_budget": {}
+  },
+  "keys": [
+    {
+      "token": "16c337f9df00a0e6472627e39a2ed02e67bc9a8a760c983c4e9b8cad7954f3c0",
+      "key_name": null,
+      "key_alias": null,
+      "spend": 200000.0,
+      "expires": null,
+      "models": [],
+      "aliases": {},
+      "config": {},
+      "user_id": "228da235-eef0-4c30-bf53-5d6ac0d278c2",
+      "team_id": null,
+      "permissions": {},
+      "max_parallel_requests": null,
+      "metadata": {},
+      "tpm_limit": null,
+      "rpm_limit": null,
+      "max_budget": null,
+      "budget_duration": null,
+      "budget_reset_at": null,
+      "allowed_cache_controls": [],
+      "model_spend": {
+        "chatgpt-v-2": 200000
+      },
+      "model_max_budget": {}
+    }
+  ],
+  "teams": []
 }
+
 ```
 
 ## Advanced 

docs/my-website/sidebars.js

@@ -123,6 +123,8 @@ const sidebars = {
         "providers/aws_sagemaker",
         "providers/bedrock",
         "providers/anyscale",
+        "providers/huggingface", 
+        "providers/ollama", 
         "providers/perplexity", 
         "providers/groq", 
         "providers/vllm", 

enterprise/utils.py

@@ -245,3 +245,103 @@ def _create_clickhouse_aggregate_tables(client=None, table_names=[]):
             """
         )
     return
+
+
+def _forecast_daily_cost(data: list):
+    import requests
+    from datetime import datetime, timedelta
+
+    first_entry = data[0]
+    last_entry = data[-1]
+
+    # get the date today
+    today_date = datetime.today().date()
+
+    today_day_month = today_date.month
+
+    # Parse the date from the first entry
+    first_entry_date = datetime.strptime(first_entry["date"], "%Y-%m-%d").date()
+    last_entry_date = datetime.strptime(last_entry["date"], "%Y-%m-%d")
+
+    print("last entry date", last_entry_date)
+
+    # Assuming today_date is a datetime object
+    today_date = datetime.now()
+
+    # Calculate the last day of the month
+    last_day_of_todays_month = datetime(
+        today_date.year, today_date.month % 12 + 1, 1
+    ) - timedelta(days=1)
+
+    # Calculate the remaining days in the month
+    remaining_days = (last_day_of_todays_month - last_entry_date).days
+
+    current_spend_this_month = 0
+    series = {}
+    for entry in data:
+        date = entry["date"]
+        spend = entry["spend"]
+        series[date] = spend
+
+        # check if the date is in this month
+        if datetime.strptime(date, "%Y-%m-%d").month == today_day_month:
+            current_spend_this_month += spend
+
+    if len(series) < 10:
+        num_items_to_fill = 11 - len(series)
+
+        # avg spend for all days in series
+        avg_spend = sum(series.values()) / len(series)
+        for i in range(num_items_to_fill):
+            # go backwards from the first entry
+            date = first_entry_date - timedelta(days=i)
+            series[date.strftime("%Y-%m-%d")] = avg_spend
+            series[date.strftime("%Y-%m-%d")] = avg_spend
+
+    payload = {"series": series, "count": remaining_days}
+    print("Prediction Data:", payload)
+
+    headers = {
+        "Content-Type": "application/json",
+    }
+
+    response = requests.post(
+        url="https://trend-api-production.up.railway.app/forecast",
+        json=payload,
+        headers=headers,
+    )
+    # check the status code
+    response.raise_for_status()
+
+    json_response = response.json()
+    forecast_data = json_response["forecast"]
+
+    # print("Forecast Data:", forecast_data)
+
+    response_data = []
+    total_predicted_spend = current_spend_this_month
+    for date in forecast_data:
+        spend = forecast_data[date]
+        entry = {
+            "date": date,
+            "predicted_spend": spend,
+        }
+        total_predicted_spend += spend
+        response_data.append(entry)
+
+    # get month as a string, Jan, Feb, etc.
+    today_month = today_date.strftime("%B")
+    predicted_spend = (
+        f"Predicted Spend for { today_month } 2024, ${total_predicted_spend}"
+    )
+    return {"response": response_data, "predicted_spend": predicted_spend}
+
+    # print(f"Date: {entry['date']}, Spend: {entry['spend']}, Response: {response.text}")
+
+
+# _forecast_daily_cost(
+#     [
+#         {"date": "2022-01-01", "spend": 100},
+
+#     ]
+# )

litellm/llms/ollama_chat.py

@@ -68,9 +68,9 @@ class OllamaConfig:
     repeat_last_n: Optional[int] = None
     repeat_penalty: Optional[float] = None
     temperature: Optional[float] = None
-    stop: Optional[
+    stop: Optional[list] = (
-        list
+        None  # stop is a list based on this - https://github.com/jmorganca/ollama/pull/442
-    ] = None  # stop is a list based on this - https://github.com/jmorganca/ollama/pull/442
+    )
     tfs_z: Optional[float] = None
     num_predict: Optional[int] = None
     top_k: Optional[int] = None
@@ -147,6 +147,11 @@ def get_ollama_response(
 
     stream = optional_params.pop("stream", False)
     format = optional_params.pop("format", None)
+
+    for m in messages:
+        if "role" in m and m["role"] == "tool":
+            m["role"] = "assistant"
+
     data = {
         "model": model,
         "messages": messages,

litellm/llms/openai.py

@@ -334,10 +334,14 @@ class OpenAIChatCompletion(BaseLLM):
                             model_response_object=model_response,
                         )
                 except Exception as e:
+                    if print_verbose is not None:
+                        print_verbose(f"openai.py: Received openai error - {str(e)}")
                     if (
                         "Conversation roles must alternate user/assistant" in str(e)
                         or "user and assistant roles should be alternating" in str(e)
                     ) and messages is not None:
+                        if print_verbose is not None:
+                            print_verbose("openai.py: REFORMATS THE MESSAGE!")
                         # reformat messages to ensure user/assistant are alternating, if there's either 2 consecutive 'user' messages or 2 consecutive 'assistant' message, add a blank 'user' or 'assistant' message to ensure compatibility
                         new_messages = []
                         for i in range(len(messages) - 1):  # type: ignore

litellm/llms/vertex_ai.py

@@ -225,6 +225,24 @@ def _gemini_vision_convert_messages(messages: list):
                 part_mime = "video/mp4"
                 google_clooud_part = Part.from_uri(img, mime_type=part_mime)
                 processed_images.append(google_clooud_part)
+            elif "base64" in img:
+                # Case 4: Images with base64 encoding
+                import base64, re
+
+                # base 64 is passed as data:image/jpeg;base64,<base-64-encoded-image>
+                image_metadata, img_without_base_64 = img.split(",")
+
+                # read mime_type from img_without_base_64=data:image/jpeg;base64
+                # Extract MIME type using regular expression
+                mime_type_match = re.match(r"data:(.*?);base64", image_metadata)
+
+                if mime_type_match:
+                    mime_type = mime_type_match.group(1)
+                else:
+                    mime_type = "image/jpeg"
+                decoded_img = base64.b64decode(img_without_base_64)
+                processed_image = Part.from_data(data=decoded_img, mime_type=mime_type)
+                processed_images.append(processed_image)
         return prompt, processed_images
     except Exception as e:
         raise e
@@ -282,7 +300,9 @@ def completion(
             f"VERTEX AI: vertex_project={vertex_project}; vertex_location={vertex_location}"
         )
         creds, _ = google.auth.default(quota_project_id=vertex_project)
-        print_verbose(f"VERTEX AI: creds={creds}")
+        print_verbose(
+            f"VERTEX AI: creds={creds}; google application credentials: {os.getenv('GOOGLE_APPLICATION_CREDENTIALS')}"
+        )
         vertexai.init(
             project=vertex_project, location=vertex_location, credentials=creds
         )

litellm/model_prices_and_context_window_backup.json

@@ -424,6 +424,22 @@
         "mode": "chat",
         "supports_function_calling": true
     },
+    "azure/mistral-large-latest": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "azure/mistral-large-2402": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "azure/ada": {
         "max_tokens": 8191,
         "input_cost_per_token": 0.0000001,
@@ -564,6 +580,20 @@
         "litellm_provider": "mistral",
         "mode": "embedding"
     },
+    "groq/llama2-70b-4096": {
+        "max_tokens": 4096,
+        "input_cost_per_token": 0.00000070,
+        "output_cost_per_token": 0.00000080,
+        "litellm_provider": "groq",
+        "mode": "chat"
+    },
+    "groq/mixtral-8x7b-32768": {
+        "max_tokens": 32768,
+        "input_cost_per_token": 0.00000027,
+        "output_cost_per_token": 0.00000027,
+        "litellm_provider": "groq",
+        "mode": "chat"
+    },
     "claude-instant-1.2": {
         "max_tokens": 100000,
         "max_output_tokens": 8191,
@@ -2040,6 +2070,36 @@
         "output_cost_per_token": 0.00000028,
         "litellm_provider": "perplexity",
         "mode": "chat"
+    },
+    "perplexity/sonar-small-chat": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.00000007,
+        "output_cost_per_token": 0.00000028,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-small-online": {
+        "max_tokens": 12000,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0.00000028,
+        "input_cost_per_request": 0.005,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-medium-chat": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.0000018,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-medium-online": {
+        "max_tokens": 12000,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0.0000018,
+        "input_cost_per_request": 0.005,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
     },
       "anyscale/mistralai/Mistral-7B-Instruct-v0.1": {
         "max_tokens": 16384, 

litellm/proxy/_experimental/out/_next/static/chunks/app/layout-a7edbef474fe2e47.js

@@ -1 +1 @@
-(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{11837:function(n,e,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(n){n.exports={style:{fontFamily:"'__Inter_c23dc8', '__Inter_Fallback_c23dc8'",fontStyle:"normal"},className:"__className_c23dc8"}}},function(n){n.O(0,[971,69,744],function(){return n(n.s=11837)}),_N_E=n.O()}]);
+(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{87421:function(n,e,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(n){n.exports={style:{fontFamily:"'__Inter_c23dc8', '__Inter_Fallback_c23dc8'",fontStyle:"normal"},className:"__className_c23dc8"}}},function(n){n.O(0,[971,69,744],function(){return n(n.s=87421)}),_N_E=n.O()}]);

litellm/proxy/_experimental/out/_next/static/chunks/main-app-9b4fb13a7db53edf.js

@@ -1 +1 @@
-(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{70377:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(70377)}),_N_E=e.O()}]);
+(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{32028:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(32028)}),_N_E=e.O()}]);

litellm/proxy/_experimental/out/_next/static/chunks/webpack-6b93c4e1d000ff14.js

@@ -1 +1 @@
-!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/a40ad0909dd7838e.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();
+!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/16eb955147cb6b2f.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();

litellm/proxy/_experimental/out/index.html

@@ -1 +1 @@
-<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-12184ee6a95c1363.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-a85b2c176012d8e5.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-e1b183dda365ec86.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-096338c8e1915716.js" async="" crossorigin=""></script><title>🚅 LiteLLM</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-12184ee6a95c1363.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/a40ad0909dd7838e.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[30280,[\"303\",\"static/chunks/303-d80f23087a9e6aec.js\",\"931\",\"static/chunks/app/page-8f65fc157f538dff.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/a40ad0909dd7838e.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"kyOCJPBB9pyUfbMKCAXr-\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_c23dc8\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"🚅 LiteLLM\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
+<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-6b93c4e1d000ff14.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-a85b2c176012d8e5.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-e1b183dda365ec86.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-9b4fb13a7db53edf.js" async="" crossorigin=""></script><title>🚅 LiteLLM</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-6b93c4e1d000ff14.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/16eb955147cb6b2f.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[9125,[\"730\",\"static/chunks/730-1411b729a1c79695.js\",\"931\",\"static/chunks/app/page-ad3e13d2fec661b5.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/16eb955147cb6b2f.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"SP1Cm97dc_3zo4HlsJJjg\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_c23dc8\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"🚅 LiteLLM\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>

litellm/proxy/_experimental/out/index.txt

@@ -1,7 +1,7 @@
 2:I[77831,[],""]
-3:I[30280,["303","static/chunks/303-d80f23087a9e6aec.js","931","static/chunks/app/page-8f65fc157f538dff.js"],""]
+3:I[9125,["730","static/chunks/730-1411b729a1c79695.js","931","static/chunks/app/page-ad3e13d2fec661b5.js"],""]
 4:I[5613,[],""]
 5:I[31778,[],""]
-0:["kyOCJPBB9pyUfbMKCAXr-",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_c23dc8","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/a40ad0909dd7838e.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
+0:["SP1Cm97dc_3zo4HlsJJjg",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_c23dc8","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/16eb955147cb6b2f.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
 6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"🚅 LiteLLM"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
 1:null

litellm/proxy/_types.py

@@ -262,7 +262,19 @@ class NewTeamRequest(LiteLLMBase):
 
 class TeamMemberAddRequest(LiteLLMBase):
     team_id: str
-    member: Optional[Member] = None
+    member: Member
+
+
+class TeamMemberDeleteRequest(LiteLLMBase):
+    team_id: str
+    user_id: Optional[str] = None
+    user_email: Optional[str] = None
+
+    @root_validator(pre=True)
+    def check_user_info(cls, values):
+        if values.get("user_id") is None and values.get("user_email") is None:
+            raise ValueError("Either user id or user email must be provided")
+        return values
 
 
 class UpdateTeamRequest(LiteLLMBase):

litellm/proxy/proxy_server.py

@@ -783,6 +783,10 @@ async def user_api_key_auth(
                 "/v2/key/info",
                 "/models",
                 "/v1/models",
+                "/global/spend/logs",
+                "/global/spend/keys",
+                "/global/spend/models",
+                "/global/predict/spend/logs",
             ]
             # check if the current route startswith any of the allowed routes
             if (
@@ -941,8 +945,7 @@ async def _PROXY_track_cost_callback(
                 raise Exception("User API key missing from custom callback.")
         else:
             if kwargs["stream"] != True or (
-                kwargs["stream"] == True
+                kwargs["stream"] == True and "complete_streaming_response" in kwargs
-                and kwargs.get("complete_streaming_response") in kwargs
             ):
                 raise Exception(
                     f"Model not in litellm model cost map. Add custom pricing - https://docs.litellm.ai/docs/proxy/custom_pricing"
@@ -1150,9 +1153,9 @@ async def update_database(
                 payload["spend"] = response_cost
                 if prisma_client is not None:
                     await prisma_client.insert_data(data=payload, table_name="spend")
-
                 elif custom_db_client is not None:
                     await custom_db_client.insert_data(payload, table_name="spend")
+
             except Exception as e:
                 verbose_proxy_logger.info(f"Update Spend Logs DB failed to execute")
 
@@ -2407,6 +2410,9 @@ async def completion(
             data["metadata"] = {}
         data["metadata"]["user_api_key"] = user_api_key_dict.api_key
         data["metadata"]["user_api_key_metadata"] = user_api_key_dict.metadata
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None
@@ -2578,6 +2584,9 @@ async def chat_completion(
         if "metadata" not in data:
             data["metadata"] = {}
         data["metadata"]["user_api_key"] = user_api_key_dict.api_key
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None
@@ -2811,6 +2820,9 @@ async def embeddings(
             "authorization", None
         )  # do not store the original `sk-..` api key in the db
         data["metadata"]["headers"] = _headers
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None
@@ -2985,6 +2997,9 @@ async def image_generation(
             "authorization", None
         )  # do not store the original `sk-..` api key in the db
         data["metadata"]["headers"] = _headers
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None
@@ -3143,6 +3158,9 @@ async def moderations(
             "authorization", None
         )  # do not store the original `sk-..` api key in the db
         data["metadata"]["headers"] = _headers
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None
@@ -4052,7 +4070,12 @@ async def view_spend_logs(
     tags=["Budget & Spend Tracking"],
     dependencies=[Depends(user_api_key_auth)],
 )
-async def global_spend_logs():
+async def global_spend_logs(
+    api_key: str = fastapi.Query(
+        default=None,
+        description="API Key to get global spend (spend per day for last 30d). Admin-only endpoint",
+    )
+):
     """
     [BETA] This is a beta endpoint. It will change.
 
@@ -4061,12 +4084,34 @@ async def global_spend_logs():
     More efficient implementation of /spend/logs, by creating a view over the spend logs table.
     """
     global prisma_client
-
+    if prisma_client is None:
+        raise ProxyException(
+            message="Prisma Client is not initialized",
+            type="internal_error",
+            param="None",
+            code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+        )
+    if api_key is None:
         sql_query = """SELECT * FROM "MonthlyGlobalSpend";"""
 
         response = await prisma_client.db.query_raw(query=sql_query)
 
         return response
+    else:
+        sql_query = (
+            """
+            SELECT * FROM "MonthlyGlobalSpendPerKey"
+            WHERE "api_key" = '"""
+            + api_key
+            + """'
+            ORDER BY "date";
+        """
+        )
+
+        response = await prisma_client.db.query_raw(query=sql_query)
+
+        return response
+    return
 
 
 @router.get(
@@ -4096,6 +4141,28 @@ async def global_spend_keys(
     return response
 
 
+@router.get(
+    "/global/spend/end_users",
+    tags=["Budget & Spend Tracking"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def global_spend_end_users():
+    """
+    [BETA] This is a beta endpoint. It will change.
+
+    Use this to get the top 'n' keys with the highest spend, ordered by spend.
+    """
+    global prisma_client
+
+    if prisma_client is None:
+        raise HTTPException(status_code=500, detail={"error": "No db connected"})
+    sql_query = f"""SELECT * FROM "Last30dTopEndUsersSpend";"""
+
+    response = await prisma_client.db.query_raw(query=sql_query)
+
+    return response
+
+
 @router.get(
     "/global/spend/models",
     tags=["Budget & Spend Tracking"],
@@ -4124,6 +4191,19 @@ async def global_spend_models(
     return response
 
 
+@router.post(
+    "/global/predict/spend/logs",
+    tags=["Budget & Spend Tracking"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def global_predict_spend_logs(request: Request):
+    from litellm.proxy.enterprise.utils import _forecast_daily_cost
+
+    data = await request.json()
+    data = data.get("data")
+    return _forecast_daily_cost(data)
+
+
 @router.get(
     "/daily_metrics",
     summary="Get daily spend metrics",
@@ -4312,6 +4392,14 @@ async def user_info(
         default=False,
         description="set to true to View all users. When using view_all, don't pass user_id",
     ),
+    page: Optional[int] = fastapi.Query(
+        default=0,
+        description="Page number for pagination. Only use when view_all is true",
+    ),
+    page_size: Optional[int] = fastapi.Query(
+        default=25,
+        description="Number of items per page. Only use when view_all is true",
+    ),
     user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
 ):
     """
@@ -4333,8 +4421,14 @@ async def user_info(
         if user_id is not None:
             user_info = await prisma_client.get_data(user_id=user_id)
         elif view_all == True:
+            if page is None:
+                page = 0
+            if page_size is None:
+                page_size = 25
+            offset = (page) * page_size  # default is 0
+            limit = page_size  # default is 10
             user_info = await prisma_client.get_data(
-                table_name="user", query_type="find_all"
+                table_name="user", query_type="find_all", offset=offset, limit=limit
             )
             return user_info
         else:
@@ -4455,31 +4549,42 @@ async def user_update(data: UpdateUserRequest):
                 non_default_values[k] = v
 
         ## ADD USER, IF NEW ##
-        if data.user_id is not None and len(data.user_id) == 0:
+        verbose_proxy_logger.debug(f"/user/update: Received data = {data}")
+        if data.user_id is not None and len(data.user_id) > 0:
             non_default_values["user_id"] = data.user_id  # type: ignore
-            await prisma_client.update_data(
+            verbose_proxy_logger.debug(f"In update user, user_id condition block.")
+            response = await prisma_client.update_data(
                 user_id=data.user_id,
                 data=non_default_values,
                 table_name="user",
             )
+            verbose_proxy_logger.debug(
+                f"received response from updating prisma client. response={response}"
+            )
         elif data.user_email is not None:
             non_default_values["user_id"] = str(uuid.uuid4())
             non_default_values["user_email"] = data.user_email
             ## user email is not unique acc. to prisma schema -> future improvement
             ### for now: check if it exists in db, if not - insert it
-            existing_user_row = await prisma_client.get_data(
+            existing_user_rows = await prisma_client.get_data(
                 key_val={"user_email": data.user_email},
                 table_name="user",
                 query_type="find_all",
             )
-            if existing_user_row is None or (
+            if existing_user_rows is None or (
-                isinstance(existing_user_row, list) and len(existing_user_row) == 0
+                isinstance(existing_user_rows, list) and len(existing_user_rows) == 0
             ):
-                await prisma_client.insert_data(
+                response = await prisma_client.insert_data(
                     data=non_default_values, table_name="user"
                 )
-
+            elif isinstance(existing_user_rows, list) and len(existing_user_rows) > 0:
-        return non_default_values
+                for existing_user in existing_user_rows:
+                    response = await prisma_client.update_data(
+                        user_id=existing_user.user_id,
+                        data=non_default_values,
+                        table_name="user",
+                    )
+        return response
         # update based on remaining passed in values
     except Exception as e:
         traceback.print_exc()
@@ -5052,6 +5157,117 @@ async def team_member_add(
     return team_row
 
 
+@router.post(
+    "/team/member_delete",
+    tags=["team management"],
+    dependencies=[Depends(user_api_key_auth)],
+)
+async def team_member_delete(
+    data: TeamMemberDeleteRequest,
+    user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
+):
+    """ 
+    [BETA]
+
+    delete members (either via user_email or user_id) from a team
+
+    If user doesn't exist, an exception will be raised
+    ```
+    curl -X POST 'http://0.0.0.0:8000/team/update' \
+    
+    -H 'Authorization: Bearer sk-1234' \
+        
+    -H 'Content-Type: application/json' \
+    
+    -D '{
+        "team_id": "45e3e396-ee08-4a61-a88e-16b3ce7e0849",
+        "member": {"role": "user", "user_id": "krrish247652@berri.ai"}
+    }'
+    ```
+    """
+    if prisma_client is None:
+        raise HTTPException(status_code=500, detail={"error": "No db connected"})
+
+    if data.team_id is None:
+        raise HTTPException(status_code=400, detail={"error": "No team id passed in"})
+
+    if data.user_id is None and data.user_email is None:
+        raise HTTPException(
+            status_code=400,
+            detail={"error": "Either user_id or user_email needs to be passed in"},
+        )
+
+    existing_team_row = await prisma_client.get_data(  # type: ignore
+        team_id=data.team_id, table_name="team", query_type="find_unique"
+    )
+
+    ## DELETE MEMBER FROM TEAM
+    new_team_members = []
+    for m in existing_team_row.members_with_roles:
+        if (
+            data.user_id is not None
+            and m["user_id"] is not None
+            and data.user_id == m["user_id"]
+        ):
+            continue
+        elif (
+            data.user_email is not None
+            and m["user_email"] is not None
+            and data.user_email == m["user_email"]
+        ):
+            continue
+        new_team_members.append(m)
+    existing_team_row.members_with_roles = new_team_members
+    complete_team_data = LiteLLM_TeamTable(
+        **existing_team_row.model_dump(),
+    )
+
+    team_row = await prisma_client.update_data(
+        update_key_values=complete_team_data.json(exclude_none=True),
+        data=complete_team_data.json(exclude_none=True),
+        table_name="team",
+        team_id=data.team_id,
+    )
+
+    ## DELETE TEAM ID from USER ROW, IF EXISTS ##
+    # get user row
+    key_val = {}
+    if data.user_id is not None:
+        key_val["user_id"] = data.user_id
+    elif data.user_email is not None:
+        key_val["user_email"] = data.user_email
+    existing_user_rows = await prisma_client.get_data(
+        key_val=key_val,
+        table_name="user",
+        query_type="find_all",
+    )
+    user_data = {  # type: ignore
+        "teams": [],
+        "models": team_row["data"].models,
+    }
+    if existing_user_rows is not None and (
+        isinstance(existing_user_rows, list) and len(existing_user_rows) > 0
+    ):
+        for existing_user in existing_user_rows:
+            team_list = []
+            if hasattr(existing_user, "teams"):
+                team_list = existing_user.teams
+                team_list.remove(data.team_id)
+                user_data["user_id"] = existing_user.user_id
+                await prisma_client.update_data(
+                    user_id=existing_user.user_id,
+                    data=user_data,
+                    update_key_values_custom_query={
+                        "teams": {
+                            "set": [team_row["team_id"]],
+                        }
+                    },
+                    table_name="user",
+                )
+
+    return team_row["data"]
+
+
 @router.post(
     "/team/delete", tags=["team management"], dependencies=[Depends(user_api_key_auth)]
 )
@@ -5535,6 +5751,9 @@ async def async_queue_request(
             "authorization", None
         )  # do not store the original `sk-..` api key in the db
         data["metadata"]["headers"] = _headers
+        data["metadata"]["user_api_key_alias"] = getattr(
+            user_api_key_dict, "key_alias", None
+        )
         data["metadata"]["user_api_key_user_id"] = user_api_key_dict.user_id
         data["metadata"]["user_api_key_team_id"] = getattr(
             user_api_key_dict, "team_id", None

litellm/proxy/schema.prisma

@@ -97,8 +97,9 @@ model LiteLLM_SpendLogs {
   cache_hit           String   @default("")
   cache_key           String   @default("")
   request_tags        Json     @default("[]")
+  team_id             String? 
+  end_user            String? 
 }
-
 // Beta - allow team members to request access to a model
 model LiteLLM_UserNotifications {
   request_id          String @unique

litellm/proxy/utils.py

@@ -542,6 +542,100 @@ class PrismaClient:
 
             print("MonthlyGlobalSpend Created!")  # noqa
 
+        try:
+            await self.db.query_raw("""SELECT 1 FROM "Last30dKeysBySpend" LIMIT 1""")
+            print("Last30dKeysBySpend Exists!")  # noqa
+        except Exception as e:
+            sql_query = """
+            CREATE OR REPLACE VIEW "Last30dKeysBySpend" AS
+            SELECT 
+            L."api_key", 
+            V."key_alias",
+            V."key_name",
+            SUM(L."spend") AS total_spend
+            FROM
+            "LiteLLM_SpendLogs" L
+            LEFT JOIN 
+            "LiteLLM_VerificationToken" V
+            ON
+            L."api_key" = V."token"
+            WHERE
+            L."startTime" >= (CURRENT_DATE - INTERVAL '30 days')
+            GROUP BY
+            L."api_key", V."key_alias", V."key_name"
+            ORDER BY
+            total_spend DESC;
+            """
+            await self.db.execute_raw(query=sql_query)
+
+            print("Last30dKeysBySpend Created!")  # noqa
+
+        try:
+            await self.db.query_raw("""SELECT 1 FROM "Last30dModelsBySpend" LIMIT 1""")
+            print("Last30dModelsBySpend Exists!")  # noqa
+        except Exception as e:
+            sql_query = """
+            CREATE OR REPLACE VIEW "Last30dModelsBySpend" AS
+            SELECT
+            "model",
+            SUM("spend") AS total_spend
+            FROM
+            "LiteLLM_SpendLogs"
+            WHERE
+            "startTime" >= (CURRENT_DATE - INTERVAL '30 days')
+            AND "model" != ''
+            GROUP BY
+            "model"
+            ORDER BY
+            total_spend DESC;
+            """
+            await self.db.execute_raw(query=sql_query)
+
+            print("Last30dModelsBySpend Created!")  # noqa
+        try:
+            await self.db.query_raw(
+                """SELECT 1 FROM "MonthlyGlobalSpendPerKey" LIMIT 1"""
+            )
+            print("MonthlyGlobalSpendPerKey Exists!")  # noqa
+        except Exception as e:
+            sql_query = """
+                CREATE OR REPLACE VIEW "MonthlyGlobalSpendPerKey" AS 
+                SELECT
+                DATE("startTime") AS date, 
+                SUM("spend") AS spend,
+                api_key as api_key
+                FROM 
+                "LiteLLM_SpendLogs" 
+                WHERE 
+                "startTime" >= (CURRENT_DATE - INTERVAL '30 days')
+                GROUP BY 
+                DATE("startTime"),
+                api_key;
+            """
+            await self.db.execute_raw(query=sql_query)
+
+            print("MonthlyGlobalSpendPerKey Created!")  # noqa
+
+        try:
+            await self.db.query_raw(
+                """SELECT 1 FROM "Last30dTopEndUsersSpend" LIMIT 1"""
+            )
+            print("Last30dTopEndUsersSpend Exists!")  # noqa
+        except Exception as e:
+            sql_query = """
+            CREATE VIEW "Last30dTopEndUsersSpend" AS
+            SELECT end_user, COUNT(*) AS total_events, SUM(spend) AS total_spend
+            FROM "LiteLLM_SpendLogs"
+            WHERE end_user <> '' AND end_user <> user
+            AND "startTime" >= CURRENT_DATE - INTERVAL '30 days'
+            GROUP BY end_user
+            ORDER BY total_spend DESC
+            LIMIT 100;
+            """
+            await self.db.execute_raw(query=sql_query)
+
+            print("Last30dTopEndUsersSpend Created!")  # noqa
+
         return
 
     @backoff.on_exception(
@@ -613,6 +707,10 @@ class PrismaClient:
         query_type: Literal["find_unique", "find_all"] = "find_unique",
         expires: Optional[datetime] = None,
         reset_at: Optional[datetime] = None,
+        offset: Optional[int] = None,  # pagination, what row number to start from
+        limit: Optional[
+            int
+        ] = None,  # pagination, number of rows to getch when find_all==True
     ):
         try:
             response: Any = None
@@ -748,7 +846,7 @@ class PrismaClient:
                         )
                     else:
                         response = await self.db.litellm_usertable.find_many(  # type: ignore
-                            order={"spend": "desc"},
+                            order={"spend": "desc"}, take=limit, skip=offset
                         )
                 return response
             elif table_name == "spend":
@@ -1034,7 +1132,7 @@ class PrismaClient:
                     + f"DB User Table - update succeeded {update_user_row}"
                     + "\033[0m"
                 )
-                return {"user_id": user_id, "data": db_data}
+                return {"user_id": user_id, "data": update_user_row}
             elif (
                 team_id is not None
                 or (table_name is not None and table_name == "team")
@@ -1473,7 +1571,12 @@ def get_logging_payload(kwargs, response_obj, start_time, end_time):
         "startTime": start_time,
         "endTime": end_time,
         "model": kwargs.get("model", ""),
-        "user": kwargs.get("user", ""),
+        "user": kwargs.get("litellm_params", {})
+        .get("metadata", {})
+        .get("user_api_key_user_id", ""),
+        "team_id": kwargs.get("litellm_params", {})
+        .get("metadata", {})
+        .get("user_api_key_team_id", ""),
         "metadata": metadata,
         "cache_key": cache_key,
         "spend": kwargs.get("response_cost", 0),
@@ -1481,6 +1584,7 @@ def get_logging_payload(kwargs, response_obj, start_time, end_time):
         "prompt_tokens": usage.get("prompt_tokens", 0),
         "completion_tokens": usage.get("completion_tokens", 0),
         "request_tags": metadata.get("tags", []),
+        "end_user": kwargs.get("user", ""),
     }
 
     verbose_proxy_logger.debug(f"SpendTable: created payload - payload: {payload}\n\n")

litellm/tests/test_amazing_vertex_completion.py

@@ -336,6 +336,52 @@ def test_gemini_pro_vision():
 # test_gemini_pro_vision()
 
 
+def encode_image(image_path):
+    import base64
+
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode("utf-8")
+
+
+@pytest.mark.skip(
+    reason="we already test gemini-pro-vision, this is just another way to pass images"
+)
+def test_gemini_pro_vision_base64():
+    try:
+        load_vertex_ai_credentials()
+        litellm.set_verbose = True
+        litellm.num_retries = 3
+        image_path = "cached_logo.jpg"
+        # Getting the base64 string
+        base64_image = encode_image(image_path)
+        resp = litellm.completion(
+            model="vertex_ai/gemini-pro-vision",
+            messages=[
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "Whats in this image?"},
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": "data:image/jpeg;base64," + base64_image
+                            },
+                        },
+                    ],
+                }
+            ],
+        )
+        print(resp)
+
+        prompt_tokens = resp.usage.prompt_tokens
+
+    except Exception as e:
+        if "500 Internal error encountered.'" in str(e):
+            pass
+        else:
+            pytest.fail(f"An exception occurred - {str(e)}")
+
+
 def test_gemini_pro_function_calling():
     load_vertex_ai_credentials()
     tools = [

litellm/tests/test_completion.py

@@ -107,6 +107,31 @@ def test_completion_mistral_api():
         pytest.fail(f"Error occurred: {e}")
 
 
+@pytest.mark.skip(
+    reason="Since we already test mistral/mistral-tiny in test_completion_mistral_api. This is only for locally verifying azure mistral works"
+)
+def test_completion_mistral_azure():
+    try:
+        litellm.set_verbose = True
+        response = completion(
+            model="mistral/Mistral-large-nmefg",
+            api_key=os.environ["MISTRAL_AZURE_API_KEY"],
+            api_base=os.environ["MISTRAL_AZURE_API_BASE"],
+            max_tokens=5,
+            messages=[
+                {
+                    "role": "user",
+                    "content": "Hi from litellm",
+                }
+            ],
+        )
+        # Add any assertions here to check the response
+        print(response)
+
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 # test_completion_mistral_api()
 
 
@@ -267,7 +292,7 @@ def test_completion_gpt4_vision():
 
 
 def test_completion_azure_gpt4_vision():
-    # azure/gpt-4, vision takes 5seconds to respond
+    # azure/gpt-4, vision takes 5 seconds to respond
     try:
         litellm.set_verbose = True
         response = completion(

litellm/utils.py

@@ -4893,7 +4893,7 @@ def get_optional_params(
             extra_body  # openai client supports `extra_body` param
         )
     else:  # assume passing in params for openai/azure openai
-        print_verbose(f"UNMAPPED PROVIDER, ASSUMING IT'S OPENAI/AZUREs")
+        print_verbose(f"UNMAPPED PROVIDER, ASSUMING IT'S OPENAI/AZURE")
         supported_params = [
             "functions",
             "function_call",
@@ -5015,8 +5015,21 @@ def get_llm_provider(
                 dynamic_api_key = get_secret("GROQ_API_KEY")
             elif custom_llm_provider == "mistral":
                 # mistral is openai compatible, we just need to set this to custom_openai and have the api_base be https://api.mistral.ai
-                api_base = api_base or "https://api.mistral.ai/v1"
+                api_base = (
-                dynamic_api_key = get_secret("MISTRAL_API_KEY")
+                    api_base
+                    or get_secret("MISTRAL_AZURE_API_BASE")  # for Azure AI Mistral
+                    or "https://api.mistral.ai/v1"
+                )
+                # if api_base does not end with /v1 we add it
+                if api_base is not None and not api_base.endswith(
+                    "/v1"
+                ):  # Mistral always needs a /v1 at the end
+                    api_base = api_base + "/v1"
+                dynamic_api_key = (
+                    api_key
+                    or get_secret("MISTRAL_AZURE_API_KEY")  # for Azure AI Mistral
+                    or get_secret("MISTRAL_API_KEY")
+                )
             elif custom_llm_provider == "voyage":
                 # voyage is openai compatible, we just need to set this to custom_openai and have the api_base be https://api.voyageai.com/v1
                 api_base = "https://api.voyageai.com/v1"
@@ -5511,7 +5524,7 @@ def validate_environment(model: Optional[str] = None) -> dict:
         }
     ## EXTRACT LLM PROVIDER - if model name provided
     try:
-        custom_llm_provider = get_llm_provider(model=model)
+        _, custom_llm_provider, _, _ = get_llm_provider(model=model)
     except:
         custom_llm_provider = None
     # # check if llm provider part of model name
@@ -5605,7 +5618,7 @@ def validate_environment(model: Optional[str] = None) -> dict:
         ## openai - chatcompletion + text completion
         if (
             model in litellm.open_ai_chat_completion_models
-            or litellm.open_ai_text_completion_models
+            or model in litellm.open_ai_text_completion_models
         ):
             if "OPENAI_API_KEY" in os.environ:
                 keys_in_environment = True

model_prices_and_context_window.json

@@ -424,6 +424,22 @@
         "mode": "chat",
         "supports_function_calling": true
     },
+    "azure/mistral-large-latest": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "azure/mistral-large-2402": {
+        "max_tokens": 32000,
+        "input_cost_per_token": 0.000008,
+        "output_cost_per_token": 0.000024,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "azure/ada": {
         "max_tokens": 8191,
         "input_cost_per_token": 0.0000001,
@@ -564,6 +580,20 @@
         "litellm_provider": "mistral",
         "mode": "embedding"
     },
+    "groq/llama2-70b-4096": {
+        "max_tokens": 4096,
+        "input_cost_per_token": 0.00000070,
+        "output_cost_per_token": 0.00000080,
+        "litellm_provider": "groq",
+        "mode": "chat"
+    },
+    "groq/mixtral-8x7b-32768": {
+        "max_tokens": 32768,
+        "input_cost_per_token": 0.00000027,
+        "output_cost_per_token": 0.00000027,
+        "litellm_provider": "groq",
+        "mode": "chat"
+    },
     "claude-instant-1.2": {
         "max_tokens": 100000,
         "max_output_tokens": 8191,
@@ -2040,6 +2070,36 @@
         "output_cost_per_token": 0.00000028,
         "litellm_provider": "perplexity",
         "mode": "chat"
+    },
+    "perplexity/sonar-small-chat": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.00000007,
+        "output_cost_per_token": 0.00000028,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-small-online": {
+        "max_tokens": 12000,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0.00000028,
+        "input_cost_per_request": 0.005,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-medium-chat": {
+        "max_tokens": 16384,
+        "input_cost_per_token": 0.0000006,
+        "output_cost_per_token": 0.0000018,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
+    },
+    "perplexity/sonar-medium-online": {
+        "max_tokens": 12000,
+        "input_cost_per_token": 0,
+        "output_cost_per_token": 0.0000018,
+        "input_cost_per_request": 0.005,
+        "litellm_provider": "perplexity",
+        "mode": "chat"
     },
       "anyscale/mistralai/Mistral-7B-Instruct-v0.1": {
         "max_tokens": 16384, 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "1.28.0"
+version = "1.28.7"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT"
@@ -74,7 +74,7 @@ requires = ["poetry-core", "wheel"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "1.28.0"
+version = "1.28.7"
 version_files = [
     "pyproject.toml:^version"
 ]

schema.prisma

@@ -97,6 +97,8 @@ model LiteLLM_SpendLogs {
   cache_hit           String   @default("")
   cache_key           String   @default("")
   request_tags        Json     @default("[]")
+  team_id             String? 
+  end_user            String?
 }
 
 // Beta - allow team members to request access to a model

tests/test_team.py

@@ -35,6 +35,25 @@ async def new_user(session, i, user_id=None, budget=None, budget_duration=None):
         return await response.json()
 
 
+async def delete_member(session, i, team_id, user_id):
+    url = "http://0.0.0.0:4000/team/member_delete"
+    headers = {"Authorization": "Bearer sk-1234", "Content-Type": "application/json"}
+    data = {"team_id": team_id, "user_id": user_id}
+
+    async with session.post(url, headers=headers, json=data) as response:
+        status = response.status
+        response_text = await response.text()
+
+        print(f"Response {i} (Status code: {status}):")
+        print(response_text)
+        print()
+
+        if status != 200:
+            raise Exception(f"Request {i} did not return a 200 status code: {status}")
+
+        return await response.json()
+
+
 async def generate_key(
     session,
     i,
@@ -290,3 +309,45 @@ async def test_team_delete():
         response = await chat_completion(session=session, key=key)
         ## Delete team
         await delete_team(session=session, i=0, team_id=team_data["team_id"])
+
+
+@pytest.mark.asyncio
+async def test_member_delete():
+    """
+    - Create team
+    - Add member
+    - Get team info (check if member in team)
+    - Delete member
+    - Get team info (check if member in team)
+    """
+    async with aiohttp.ClientSession() as session:
+        # Create Team
+        ## Create admin
+        admin_user = f"{uuid.uuid4()}"
+        await new_user(session=session, i=0, user_id=admin_user)
+        ## Create normal user
+        normal_user = f"{uuid.uuid4()}"
+        print(f"normal_user: {normal_user}")
+        await new_user(session=session, i=0, user_id=normal_user)
+        ## Create team with 1 admin and 1 user
+        member_list = [
+            {"role": "admin", "user_id": admin_user},
+            {"role": "user", "user_id": normal_user},
+        ]
+        team_data = await new_team(session=session, i=0, member_list=member_list)
+        print(f"team_data: {team_data}")
+        member_id_list = []
+        for member in team_data["members_with_roles"]:
+            member_id_list.append(member["user_id"])
+
+        assert normal_user in member_id_list
+        # Delete member
+        updated_team_data = await delete_member(
+            session=session, i=0, team_id=team_data["team_id"], user_id=normal_user
+        )
+        print(f"updated_team_data: {updated_team_data}")
+        member_id_list = []
+        for member in updated_team_data["members_with_roles"]:
+            member_id_list.append(member["user_id"])
+
+        assert normal_user not in member_id_list

ui/litellm-dashboard/out/_next/static/SP1Cm97dc_3zo4HlsJJjg/_buildManifest.js

@@ -0,0 +1 @@
+self.__BUILD_MANIFEST={__rewrites:{afterFiles:[],beforeFiles:[],fallback:[]},"/_error":["static/chunks/pages/_error-d6107f1aac0c574c.js"],sortedPages:["/_app","/_error"]},self.__BUILD_MANIFEST_CB&&self.__BUILD_MANIFEST_CB();

ui/litellm-dashboard/out/_next/static/SP1Cm97dc_3zo4HlsJJjg/_ssgManifest.js

@@ -0,0 +1 @@
+self.__SSG_MANIFEST=new Set([]);self.__SSG_MANIFEST_CB&&self.__SSG_MANIFEST_CB()

ui/litellm-dashboard/out/_next/static/chunks/app/layout-a7edbef474fe2e47.js

@@ -0,0 +1 @@
+(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{87421:function(n,e,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(n){n.exports={style:{fontFamily:"'__Inter_c23dc8', '__Inter_Fallback_c23dc8'",fontStyle:"normal"},className:"__className_c23dc8"}}},function(n){n.O(0,[971,69,744],function(){return n(n.s=87421)}),_N_E=n.O()}]);

ui/litellm-dashboard/out/_next/static/chunks/main-app-9b4fb13a7db53edf.js

@@ -0,0 +1 @@
+(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{32028:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(32028)}),_N_E=e.O()}]);

ui/litellm-dashboard/out/_next/static/chunks/webpack-6b93c4e1d000ff14.js

@@ -0,0 +1 @@
+!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/16eb955147cb6b2f.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();

ui/litellm-dashboard/out/index.html

@@ -1 +1 @@
-<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-12184ee6a95c1363.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-a85b2c176012d8e5.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-e1b183dda365ec86.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-096338c8e1915716.js" async="" crossorigin=""></script><title>🚅 LiteLLM</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-12184ee6a95c1363.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/a40ad0909dd7838e.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[30280,[\"303\",\"static/chunks/303-d80f23087a9e6aec.js\",\"931\",\"static/chunks/app/page-8f65fc157f538dff.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/a40ad0909dd7838e.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"kyOCJPBB9pyUfbMKCAXr-\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_c23dc8\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"🚅 LiteLLM\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
+<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-6b93c4e1d000ff14.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-a85b2c176012d8e5.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-e1b183dda365ec86.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-9b4fb13a7db53edf.js" async="" crossorigin=""></script><title>🚅 LiteLLM</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-6b93c4e1d000ff14.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/16eb955147cb6b2f.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[9125,[\"730\",\"static/chunks/730-1411b729a1c79695.js\",\"931\",\"static/chunks/app/page-ad3e13d2fec661b5.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/16eb955147cb6b2f.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"SP1Cm97dc_3zo4HlsJJjg\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_c23dc8\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"🚅 LiteLLM\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>

ui/litellm-dashboard/out/index.txt

@@ -1,7 +1,7 @@
 2:I[77831,[],""]
-3:I[30280,["303","static/chunks/303-d80f23087a9e6aec.js","931","static/chunks/app/page-8f65fc157f538dff.js"],""]
+3:I[9125,["730","static/chunks/730-1411b729a1c79695.js","931","static/chunks/app/page-ad3e13d2fec661b5.js"],""]
 4:I[5613,[],""]
 5:I[31778,[],""]
-0:["kyOCJPBB9pyUfbMKCAXr-",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_c23dc8","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/a40ad0909dd7838e.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
+0:["SP1Cm97dc_3zo4HlsJJjg",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_c23dc8","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/16eb955147cb6b2f.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
 6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"🚅 LiteLLM"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
 1:null

ui/litellm-dashboard/src/app/page.tsx

@@ -11,8 +11,10 @@ import ChatUI from "@/components/chat_ui";
 import Sidebar from "../components/leftnav";
 import Usage from "../components/usage";
 import { jwtDecode } from "jwt-decode";
+import { Typography } from "antd";
 
 const CreateKeyPage = () => {
+  const { Title, Paragraph } = Typography;
   const [userRole, setUserRole] = useState("");
   const [userEmail, setUserEmail] = useState<null | string>(null);
   const [teams, setTeams] = useState<null | any[]>(null);
@@ -41,6 +43,9 @@ const CreateKeyPage = () => {
           const formattedUserRole = formatUserRole(decoded.user_role);
           console.log("Decoded user_role:", formattedUserRole);
           setUserRole(formattedUserRole);
+          if (formattedUserRole == "Admin Viewer") {
+            setPage("usage");
+          }
         } else {
           console.log("User role not defined");
         }
@@ -66,7 +71,8 @@ const CreateKeyPage = () => {
     if (!userRole) {
       return "Undefined Role";
     }
-    console.log(`Received user role: ${userRole}`);
+    console.log(`Received user role: ${userRole.toLowerCase()}`);
+    console.log(`Received user role length: ${userRole.toLowerCase().length}`);
     switch (userRole.toLowerCase()) {
       case "app_owner":
         return "App Owner";

ui/litellm-dashboard/src/components/admins.tsx

@@ -138,10 +138,13 @@ const AdminPanel: React.FC<AdminPanelProps> = ({
   console.log(`admins: ${admins?.length}`);
   return (
     <div className="w-full m-2">
-      <Title level={4}>Proxy Admins</Title>
+      <Title level={4}>Restricted Access</Title>
       <Paragraph>
-        Add other people to just view global spend. They cannot create teams or
+        Add other people to just view spend. They cannot create keys, teams or
-        grant users access to new models.
+        grant users access to new models.{" "}
+        <a href="https://docs.litellm.ai/docs/proxy/ui#restrict-ui-access">
+          Requires SSO Setup
+        </a>
       </Paragraph>
       <Grid numItems={1} className="gap-2 p-0 w-full">
         <Col numColSpan={1}>

ui/litellm-dashboard/src/components/chat_ui.tsx

@@ -21,6 +21,7 @@ import {
 import { modelAvailableCall } from "./networking";
 import openai from "openai";
 import { Prism as SyntaxHighlighter } from "react-syntax-highlighter";
+import { Typography } from "antd";
 
 interface ChatUIProps {
   accessToken: string | null;
@@ -145,6 +146,16 @@ const ChatUI: React.FC<ChatUIProps> = ({
     setInputMessage("");
   };
 
+  if (userRole && userRole == "Admin Viewer") {
+    const { Title, Paragraph } = Typography;
+    return (
+      <div>
+        <Title level={1}>Access Denied</Title>
+        <Paragraph>Ask your proxy admin for access to test models</Paragraph>
+      </div>
+    );
+  }
+
   return (
     <div style={{ width: "100%", position: "relative" }}>
       <Grid className="gap-2 p-10 h-[75vh] w-full">

ui/litellm-dashboard/src/components/leftnav.tsx

@@ -16,6 +16,34 @@ const Sidebar: React.FC<SidebarProps> = ({
   userRole,
   defaultSelectedKey,
 }) => {
+  if (userRole == "Admin Viewer") {
+    return (
+      <Layout style={{ minHeight: "100vh", maxWidth: "120px" }}>
+        <Sider width={120}>
+          <Menu
+            mode="inline"
+            defaultSelectedKeys={
+              defaultSelectedKey ? defaultSelectedKey : ["4"]
+            }
+            style={{ height: "100%", borderRight: 0 }}
+          >
+            <Menu.Item key="4" onClick={() => setPage("api-keys")}>
+              API Keys
+            </Menu.Item>
+            <Menu.Item key="2" onClick={() => setPage("models")}>
+              Models
+            </Menu.Item>
+            <Menu.Item key="3" onClick={() => setPage("llm-playground")}>
+              Chat UI
+            </Menu.Item>
+            <Menu.Item key="1" onClick={() => setPage("usage")}>
+              Usage
+            </Menu.Item>
+          </Menu>
+        </Sider>
+      </Layout>
+    );
+  }
   return (
     <Layout style={{ minHeight: "100vh", maxWidth: "120px" }}>
       <Sider width={120}>

ui/litellm-dashboard/src/components/model_dashboard.tsx

@@ -1,8 +1,20 @@
 import React, { useState, useEffect } from "react";
-import { Card, Title, Subtitle, Table, TableHead, TableRow, TableCell, TableBody, Metric, Grid } from "@tremor/react";
+import {
+  Card,
+  Title,
+  Subtitle,
+  Table,
+  TableHead,
+  TableRow,
+  TableCell,
+  TableBody,
+  Metric,
+  Grid,
+} from "@tremor/react";
 import { modelInfoCall, userGetRequesedtModelsCall } from "./networking";
-import { Badge, BadgeDelta, Button } from '@tremor/react';
+import { Badge, BadgeDelta, Button } from "@tremor/react";
 import RequestAccess from "./request_model_access";
+import { Typography } from "antd";
 
 interface ModelDashboardProps {
   accessToken: string | null;
@@ -20,7 +32,6 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
   const [modelData, setModelData] = useState<any>({ data: [] });
   const [pendingRequests, setPendingRequests] = useState<any[]>([]);
 
-
   useEffect(() => {
     if (!accessToken || !token || !userRole || !userID) {
       return;
@@ -28,7 +39,11 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
     const fetchData = async () => {
       try {
         // Replace with your actual API call for model data
-        const modelDataResponse = await modelInfoCall(accessToken, userID,  userRole);
+        const modelDataResponse = await modelInfoCall(
+          accessToken,
+          userID,
+          userRole
+        );
         console.log("Model data response:", modelDataResponse.data);
         setModelData(modelDataResponse);
 
@@ -38,7 +53,6 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
           console.log("Pending Requests:", pendingRequests);
           setPendingRequests(user_requests.requests || []);
         }
-
       } catch (error) {
         console.error("There was an error fetching the model data", error);
       }
@@ -67,9 +81,9 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
 
     let defaultProvider = "openai";
     let provider = "";
-    let input_cost = "Undefined"
+    let input_cost = "Undefined";
-    let output_cost = "Undefined"
+    let output_cost = "Undefined";
-    let max_tokens = "Undefined"
+    let max_tokens = "Undefined";
 
     // Check if litellm_model_name is null or undefined
     if (litellm_model_name) {
@@ -81,7 +95,6 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
 
       // If there is only one element, default provider to openai
       provider = splitModel.length === 1 ? defaultProvider : firstElement;
-        
     } else {
       // litellm_model_name is null or undefined, default provider to openai
       provider = defaultProvider;
@@ -91,20 +104,29 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
       input_cost = model_info?.input_cost_per_token;
       output_cost = model_info?.output_cost_per_token;
       max_tokens = model_info?.max_tokens;
-
     }
-    modelData.data[i].provider = provider
+    modelData.data[i].provider = provider;
-    modelData.data[i].input_cost = input_cost
+    modelData.data[i].input_cost = input_cost;
-    modelData.data[i].output_cost = output_cost
+    modelData.data[i].output_cost = output_cost;
-    modelData.data[i].max_tokens = max_tokens
+    modelData.data[i].max_tokens = max_tokens;
 
     all_models_on_proxy.push(curr_model.model_name);
 
     console.log(modelData.data[i]);
-
   }
   // when users click request access show pop up to allow them to request access
 
+  if (userRole && userRole == "Admin Viewer") {
+    const { Title, Paragraph } = Typography;
+    return (
+      <div>
+        <Title level={1}>Access Denied</Title>
+        <Paragraph>
+          Ask your proxy admin for access to view all models
+        </Paragraph>
+      </div>
+    );
+  }
 
   return (
     <div style={{ width: "100%" }}>
@@ -113,64 +135,101 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
           <Table className="mt-5">
             <TableHead>
               <TableRow>
-              <TableCell><Title>Model Name </Title></TableCell>
+                <TableCell>
-              <TableCell><Title>Provider</Title></TableCell>
+                  <Title>Model Name </Title>
-              <TableCell><Title>Access</Title></TableCell>
+                </TableCell>
-              <TableCell><Title>Input Price per token ($)</Title></TableCell>
+                <TableCell>
-              <TableCell><Title>Output Price per token ($)</Title></TableCell>
+                  <Title>Provider</Title>
-              <TableCell><Title>Max Tokens</Title></TableCell>
+                </TableCell>
+                <TableCell>
+                  <Title>Access</Title>
+                </TableCell>
+                <TableCell>
+                  <Title>Input Price per token ($)</Title>
+                </TableCell>
+                <TableCell>
+                  <Title>Output Price per token ($)</Title>
+                </TableCell>
+                <TableCell>
+                  <Title>Max Tokens</Title>
+                </TableCell>
               </TableRow>
             </TableHead>
             <TableBody>
               {modelData.data.map((model: any) => (
                 <TableRow key={model.model_name}>
-
+                  <TableCell>
-                <TableCell><Title>{model.model_name}</Title></TableCell>
+                    <Title>{model.model_name}</Title>
+                  </TableCell>
                   <TableCell>{model.provider}</TableCell>
 
                   <TableCell>
-                  {model.user_access ? <Badge color={"green"}>Yes</Badge> : <RequestAccess userModels={all_models_on_proxy} accessToken={accessToken} userID={userID}></RequestAccess>}
+                    {model.user_access ? (
+                      <Badge color={"green"}>Yes</Badge>
+                    ) : (
+                      <RequestAccess
+                        userModels={all_models_on_proxy}
+                        accessToken={accessToken}
+                        userID={userID}
+                      ></RequestAccess>
+                    )}
                   </TableCell>
 
                   <TableCell>{model.input_cost}</TableCell>
                   <TableCell>{model.output_cost}</TableCell>
                   <TableCell>{model.max_tokens}</TableCell>
-
-
                 </TableRow>
               ))}
             </TableBody>
           </Table>
         </Card>
-      {
+        {userRole === "Admin" &&
-        userRole === "Admin" && pendingRequests && pendingRequests.length > 0 ? (
+        pendingRequests &&
+        pendingRequests.length > 0 ? (
           <Card>
             <Table>
               <TableHead>
                 <Title>Pending Requests</Title>
                 <TableRow>
-                  <TableCell><Title>User ID</Title></TableCell>
+                  <TableCell>
-                  <TableCell><Title>Requested Models</Title></TableCell>
+                    <Title>User ID</Title>
-                  <TableCell><Title>Justification</Title></TableCell>
+                  </TableCell>
-                  <TableCell><Title>Justification</Title></TableCell>
+                  <TableCell>
+                    <Title>Requested Models</Title>
+                  </TableCell>
+                  <TableCell>
+                    <Title>Justification</Title>
+                  </TableCell>
+                  <TableCell>
+                    <Title>Justification</Title>
+                  </TableCell>
                 </TableRow>
               </TableHead>
               <TableBody>
                 {pendingRequests.map((request: any) => (
                   <TableRow key={request.request_id}>
-                    <TableCell><p>{request.user_id}</p></TableCell>
+                    <TableCell>
-                    <TableCell><p>{request.models[0]}</p></TableCell>
+                      <p>{request.user_id}</p>
-                    <TableCell><p>{request.justification}</p></TableCell>
+                    </TableCell>
-                    <TableCell><p>{request.user_id}</p></TableCell>
+                    <TableCell>
+                      <p>{request.models[0]}</p>
+                    </TableCell>
+                    <TableCell>
+                      <p>{request.justification}</p>
+                    </TableCell>
+                    <TableCell>
+                      <p>{request.user_id}</p>
+                    </TableCell>
                     <Button>Approve</Button>
-                    <Button variant="secondary" className="ml-2">Deny</Button>
+                    <Button variant="secondary" className="ml-2">
+                      Deny
+                    </Button>
                   </TableRow>
                 ))}
               </TableBody>
             </Table>
           </Card>
-        ) : null
+        ) : null}
-      }
       </Grid>
     </div>
   );

ui/litellm-dashboard/src/components/networking.tsx

@@ -280,7 +280,7 @@ export const modelAvailableCall = async (
 
 export const keySpendLogsCall = async (accessToken: String, token: String) => {
   try {
-    const url = proxyBaseUrl ? `${proxyBaseUrl}/spend/logs` : `/spend/logs`;
+    const url = proxyBaseUrl ? `${proxyBaseUrl}/global/spend/logs` : `/global/spend/logs`;
     console.log("in keySpendLogsCall:", url);
     const response = await fetch(`${url}/?api_key=${token}`, {
       method: "GET",
@@ -404,13 +404,13 @@ export const adminTopKeysCall = async (accessToken: String) => {
   }
 };
 
-export const adminTopModelsCall = async (accessToken: String) => {
+export const adminTopEndUsersCall = async (accessToken: String) => {
   try {
     let url = proxyBaseUrl
-      ? `${proxyBaseUrl}/global/spend/models?limit=5`
+      ? `${proxyBaseUrl}/global/spend/end_users`
-      : `/global/spend/models?limit=5`;
+      : `/global/spend/end_users`;
 
-    message.info("Making spend models request");
+    message.info("Making top end users request");
     const response = await fetch(url, {
       method: "GET",
       headers: {
@@ -426,7 +426,37 @@ export const adminTopModelsCall = async (accessToken: String) => {
 
     const data = await response.json();
     console.log(data);
-    message.success("Spend Logs received");
+    message.success("Top End users received");
+    return data;
+  } catch (error) {
+    console.error("Failed to create key:", error);
+    throw error;
+  }
+};
+
+export const adminTopModelsCall = async (accessToken: String) => {
+  try {
+    let url = proxyBaseUrl
+      ? `${proxyBaseUrl}/global/spend/models?limit=5`
+      : `/global/spend/models?limit=5`;
+
+    message.info("Making top models request");
+    const response = await fetch(url, {
+      method: "GET",
+      headers: {
+        Authorization: `Bearer ${accessToken}`,
+        "Content-Type": "application/json",
+      },
+    });
+    if (!response.ok) {
+      const errorData = await response.text();
+      message.error(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+    const data = await response.json();
+    console.log(data);
+    message.success("Top Models received");
     return data;
   } catch (error) {
     console.error("Failed to create key:", error);
@@ -718,3 +748,42 @@ export const userUpdateUserCall = async (
     throw error;
   }
 };
+
+
+export const PredictedSpendLogsCall = async (accessToken: string, requestData: any) => {
+  try {
+    let url = proxyBaseUrl
+      ? `${proxyBaseUrl}/global/predict/spend/logs`
+      : `/global/predict/spend/logs`;
+
+    //message.info("Predicting spend logs request");
+
+    const response = await fetch(url, {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${accessToken}`,
+        "Content-Type": "application/json",
+      },
+      body: JSON.stringify(
+        {
+          data: requestData
+        }
+      ),
+    });
+
+    if (!response.ok) {
+      const errorData = await response.text();
+      message.error(errorData);
+      throw new Error("Network response was not ok");
+    }
+
+    const data = await response.json();
+    console.log(data);
+    //message.success("Predicted Logs received");
+    return data;
+  } catch (error) {
+    console.error("Failed to create key:", error);
+    throw error;
+  }
+};
+

ui/litellm-dashboard/src/components/usage.tsx

@@ -132,6 +132,7 @@ const UsagePage: React.FC<UsagePageProps> = ({
   const currentDate = new Date();
   const [keySpendData, setKeySpendData] = useState<any[]>([]);
   const [topKeys, setTopKeys] = useState<any[]>([]);
+  const [topModels, setTopModels] = useState<any[]>([]);
   const [topUsers, setTopUsers] = useState<any[]>([]);
 
   const firstDay = new Date(
@@ -175,7 +176,7 @@ const UsagePage: React.FC<UsagePageProps> = ({
            * If user is App Owner - use the normal spend logs call
            */
           console.log(`user role: ${userRole}`);
-          if (userRole == "Admin") {
+          if (userRole == "Admin" || userRole == "Admin Viewer") {
             const overall_spend = await adminSpendLogsCall(accessToken);
             setKeySpendData(overall_spend);
             const top_keys = await adminTopKeysCall(accessToken);
@@ -188,6 +189,11 @@ const UsagePage: React.FC<UsagePageProps> = ({
             }));
             setTopKeys(filtered_keys);
             const top_models = await adminTopModelsCall(accessToken);
+            const filtered_models = top_models.map((k: any) => ({
+              key: k["model"],
+              spend: k["total_spend"],
+            }));
+            setTopModels(filtered_models);
           } else if (userRole == "App Owner") {
             await userSpendLogsCall(
               accessToken,
@@ -242,7 +248,7 @@ const UsagePage: React.FC<UsagePageProps> = ({
             <Title>Monthly Spend</Title>
             <BarChart
               data={keySpendData}
-              index="startTime"
+              index="date"
               categories={["spend"]}
               colors={["blue"]}
               valueFormatter={valueFormatter}
@@ -285,6 +291,22 @@ const UsagePage: React.FC<UsagePageProps> = ({
             />
           </Card>
         </Col>
+        <Col numColSpan={1}>
+          <Card>
+            <Title>Top Models</Title>
+            <BarChart
+              className="mt-4 h-40"
+              data={topModels}
+              index="key"
+              categories={["spend"]}
+              colors={["blue"]}
+              yAxisWidth={200}
+              layout="vertical"
+              showXAxis={false}
+              showLegend={false}
+            />
+          </Card>
+        </Col>
       </Grid>
     </div>
   );

ui/litellm-dashboard/src/components/user_dashboard.tsx

@@ -8,7 +8,7 @@ import ViewUserSpend from "./view_user_spend";
 import DashboardTeam from "./dashboard_default_team";
 import { useSearchParams, useRouter } from "next/navigation";
 import { jwtDecode } from "jwt-decode";
-
+import { Typography } from "antd";
 const isLocal = process.env.NODE_ENV === "development";
 console.log("isLocal:", isLocal);
 const proxyBaseUrl = isLocal ? "http://localhost:4000" : null;
@@ -73,6 +73,10 @@ const UserDashboard: React.FC<UserDashboardProps> = ({
         return "App Owner";
       case "app_admin":
         return "Admin";
+      case "proxy_admin":
+        return "Admin";
+      case "proxy_admin_viewer":
+        return "Admin Viewer";
       case "app_user":
         return "App User";
       default:
@@ -180,6 +184,16 @@ const UserDashboard: React.FC<UserDashboardProps> = ({
     setUserRole("App Owner");
   }
 
+  if (userRole && userRole == "Admin Viewer") {
+    const { Title, Paragraph } = Typography;
+    return (
+      <div>
+        <Title level={1}>Access Denied</Title>
+        <Paragraph>Ask your proxy admin for access to create keys</Paragraph>
+      </div>
+    );
+  }
+
   return (
     <div>
       <Grid numItems={1} className="gap-0 p-10 h-[75vh] w-full">

ui/litellm-dashboard/src/components/view_key_spend_report.tsx

@@ -21,7 +21,7 @@ import {
   BarList,
   Metric,
 } from "@tremor/react";
-import { keySpendLogsCall } from "./networking";
+import { keySpendLogsCall, PredictedSpendLogsCall } from "./networking";
 
 interface ViewKeySpendReportProps {
   token: string;
@@ -48,6 +48,7 @@ const ViewKeySpendReport: React.FC<ViewKeySpendReportProps> = ({
   const [data, setData] = useState<{ day: string; spend: number }[] | null>(
     null
   );
+  const [predictedSpendString, setPredictedSpendString] = useState("");
   const [userData, setUserData] = useState<
     { name: string; value: number }[] | null
   >(null);
@@ -78,85 +79,25 @@ const ViewKeySpendReport: React.FC<ViewKeySpendReportProps> = ({
         (token = token)
       );
       console.log("Response:", response);
-      // loop through response
+      setData(response);
-      // get spend, startTime for each element, place in new array
 
-      const pricePerDay: Record<string, number> = (
+      // predict spend based on response
-        Object.values(response) as ResponseValueType[]
+      const predictedSpend = await PredictedSpendLogsCall(accessToken, response);
-      ).reduce((acc: Record<string, number>, value) => {
+      console.log("Response2:", predictedSpend);
-        const startTime = new Date(value.startTime);
-        const day = new Intl.DateTimeFormat("en-US", {
-          day: "2-digit",
-          month: "short",
-        }).format(startTime);
 
-        acc[day] = (acc[day] || 0) + value.spend;
+      // append predictedSpend to data
+      const combinedData = [...response, ...predictedSpend.response];
+      setData(combinedData);
+      setPredictedSpendString(predictedSpend.predicted_spend)
 
-        return acc;
+      console.log("Combined Data:", combinedData);
-      }, {});
+      // setPredictedSpend(predictedSpend);
       
-      // sort pricePerDay by day
-      // Convert object to array of key-value pairs
-      const pricePerDayArray = Object.entries(pricePerDay);
-
-      // Sort the array based on the date (key)
-      pricePerDayArray.sort(([aKey], [bKey]) => {
-        const dateA = new Date(aKey);
-        const dateB = new Date(bKey);
-        return dateA.getTime() - dateB.getTime();
-      });
-
-      // Convert the sorted array back to an object
-      const sortedPricePerDay = Object.fromEntries(pricePerDayArray);
-
-      console.log(sortedPricePerDay);
-
-      const pricePerUser: Record<string, number> = (
-        Object.values(response) as ResponseValueType[]
-      ).reduce((acc: Record<string, number>, value) => {
-        const user = value.user;
-        acc[user] = (acc[user] || 0) + value.spend;
-
-        return acc;
-      }, {});
-
-      console.log(pricePerDay);
-      console.log(pricePerUser);
-
-      const arrayBarChart = [];
-      // [
-      // {
-      //     "day": "02 Feb",
-      //     "spend": pricePerDay["02 Feb"],
-      // }
-      // ]
-      for (const [key, value] of Object.entries(sortedPricePerDay)) {
-        arrayBarChart.push({ day: key, spend: value });
-      }
-
-      // get 5 most expensive users
-      const sortedUsers = Object.entries(pricePerUser).sort(
-        (a, b) => b[1] - a[1]
-      );
-      const top5Users = sortedUsers.slice(0, 5);
-      const userChart = top5Users.map(([key, value]) => ({
-        name: key,
-        value: value,
-      }));
-
-      setData(arrayBarChart);
-      setUserData(userChart);
-      console.log("arrayBarChart:", arrayBarChart);
     } catch (error) {
       console.error("There was an error fetching the data", error);
-      // Optionally, update your UI to reflect the error state here as well
     }
   };
 
-  // useEffect(() => {
-  //   // Fetch data only when the token changes
-  //   fetchData();
-  // }, [token]); // Dependency array containing the 'token' variable
 
   if (!token) {
     return null;
@@ -164,12 +105,12 @@ const ViewKeySpendReport: React.FC<ViewKeySpendReportProps> = ({
 
   return (
     <div>
-      <Button className="mx-auto" onClick={showModal}>
+      <Button size = "xs" onClick={showModal}>
         View Spend Report
       </Button>
       <Modal
         visible={isModalVisible}
-        width={1000}
+        width={1400}
         onOk={handleOk}
         onCancel={handleCancel}
         footer={null}
@@ -177,25 +118,21 @@ const ViewKeySpendReport: React.FC<ViewKeySpendReportProps> = ({
         <Title style={{ textAlign: "left" }}>Key Name: {keyName}</Title>
 
         <Metric>Monthly Spend ${keySpend}</Metric>
+        <Title>{predictedSpendString}</Title>
 
         <Card className="mt-6 mb-6">
           {data && (
             <BarChart
               className="mt-6"
               data={data}
-              colors={["green"]}
+              colors={["blue", "amber"]}
-              index="day"
+              index="date"
-              categories={["spend"]}
+              categories={["spend", "predicted_spend"]}
-              yAxisWidth={48}
+              yAxisWidth={80}
             />
           )}
         </Card>
-        <Title className="mt-6">Top 5 Users Spend (USD)</Title>
+  
-        <Card className="mb-6">
-          {userData && (
-            <BarList className="mt-6" data={userData} color="teal" />
-          )}
-        </Card>
       </Modal>
     </div>
   );

ui/litellm-dashboard/src/components/view_key_table.tsx

@@ -86,6 +86,7 @@ const ViewKeyTable: React.FC<ViewKeyTableProps> = ({
             <TableHeaderCell>Secret Key</TableHeaderCell>
             <TableHeaderCell>Spend (USD)</TableHeaderCell>
             <TableHeaderCell>Key Budget (USD)</TableHeaderCell>
+            <TableHeaderCell>Spend Report</TableHeaderCell>
             <TableHeaderCell>Team ID</TableHeaderCell>
             <TableHeaderCell>Metadata</TableHeaderCell>
             <TableHeaderCell>Models</TableHeaderCell>
@@ -122,6 +123,15 @@ const ViewKeyTable: React.FC<ViewKeyTableProps> = ({
                     <Text>Unlimited Budget</Text>
                   )}
                 </TableCell>
+                <TableCell>
+                  <ViewKeySpendReport
+                    token={item.token}
+                    accessToken={accessToken}
+                    keySpend={item.spend}
+                    keyBudget={item.max_budget}
+                    keyName={item.key_name}
+                  />
+                </TableCell>
                 <TableCell>
                   <Text>{item.team_id}</Text>
                 </TableCell>
@@ -152,15 +162,6 @@ const ViewKeyTable: React.FC<ViewKeyTableProps> = ({
                     size="sm"
                   />
                 </TableCell>
-                <TableCell>
-                  <ViewKeySpendReport
-                    token={item.token}
-                    accessToken={accessToken}
-                    keySpend={item.spend}
-                    keyBudget={item.max_budget}
-                    keyName={item.key_name}
-                  />
-                </TableCell>
               </TableRow>
             );
           })}

ui/litellm-dashboard/src/components/view_users.tsx

@@ -1,7 +1,24 @@
 import React, { useState, useEffect } from "react";
-import { Card, Title, Subtitle, Table, TableHead, TableRow, TableCell, TableBody, Metric, Grid } from "@tremor/react";
+import {
-import { userInfoCall } from "./networking";
+  Card,
-import { Badge, BadgeDelta, Button } from '@tremor/react';
+  Title,
+  Subtitle,
+  Table,
+  TableHead,
+  TableHeaderCell,
+  TableRow,
+  TableCell,
+  TableBody,
+  Tab,
+  TabGroup,
+  TabList,
+  TabPanels,
+  Metric,
+  Grid,
+  TabPanel,
+} from "@tremor/react";
+import { userInfoCall, adminTopEndUsersCall } from "./networking";
+import { Badge, BadgeDelta, Button } from "@tremor/react";
 import RequestAccess from "./request_model_access";
 import CreateUser from "./create_user_button";
 
@@ -18,9 +35,10 @@ const ViewUserDashboard: React.FC<ViewUserDashboardProps> = ({
   userRole,
   userID,
 }) => {
-  const [userData, setuserData] = useState<null | any[]>(null);
+  const [userData, setUserData] = useState<null | any[]>(null);
-  const [pendingRequests, setPendingRequests] = useState<any[]>([]);
+  const [endUsers, setEndUsers] = useState<null | any[]>(null);
-
+  const [currentPage, setCurrentPage] = useState(1);
+  const defaultPageSize = 25;
 
   useEffect(() => {
     if (!accessToken || !token || !userRole || !userID) {
@@ -29,18 +47,39 @@ const ViewUserDashboard: React.FC<ViewUserDashboardProps> = ({
     const fetchData = async () => {
       try {
         // Replace with your actual API call for model data
-        const userDataResponse = await userInfoCall(accessToken, null,  userRole, true);
+        const userDataResponse = await userInfoCall(
+          accessToken,
+          null,
+          userRole,
+          true
+        );
         console.log("user data response:", userDataResponse);
-        setuserData(userDataResponse);
+        setUserData(userDataResponse);
-
       } catch (error) {
         console.error("There was an error fetching the model data", error);
       }
     };
 
-    if (accessToken && token && userRole && userID) {
+    if (accessToken && token && userRole && userID && !userData) {
       fetchData();
     }
+
+    const fetchEndUserSpend = async () => {
+      try {
+        const topEndUsers = await adminTopEndUsersCall(accessToken);
+        console.log("user data response:", topEndUsers);
+        setEndUsers(topEndUsers);
+      } catch (error) {
+        console.error("There was an error fetching the model data", error);
+      }
+    };
+    if (
+      userRole &&
+      (userRole == "Admin" || userRole == "Admin Viewer") &&
+      !endUsers
+    ) {
+      fetchEndUserSpend();
+    }
   }, [accessToken, token, userRole, userID]);
 
   if (!userData) {
@@ -51,40 +90,106 @@ const ViewUserDashboard: React.FC<ViewUserDashboardProps> = ({
     return <div>Loading...</div>;
   }
 
-  // when users click request access show pop up to allow them to request access
+  function renderPagination() {
+    if (!userData) return null;
+
+    const totalPages = Math.ceil(userData.length / defaultPageSize);
+    const startItem = (currentPage - 1) * defaultPageSize + 1;
+    const endItem = Math.min(currentPage * defaultPageSize, userData.length);
+
+    return (
+      <div className="flex justify-between items-center">
+        <div>
+          Showing {startItem} – {endItem} of {userData.length}
+        </div>
+        <div className="flex">
+          <button
+            className="bg-blue-500 hover:bg-blue-700 text-white font-bold py-2 px-4 rounded-l focus:outline-none"
+            disabled={currentPage === 1}
+            onClick={() => setCurrentPage(currentPage - 1)}
+          >
+            &larr; Prev
+          </button>
+          <button
+            className="bg-blue-500 hover:bg-blue-700 text-white font-bold py-2 px-4 rounded-r focus:outline-none"
+            disabled={currentPage === totalPages}
+            onClick={() => setCurrentPage(currentPage + 1)}
+          >
+            Next &rarr;
+          </button>
+        </div>
+      </div>
+    );
+  }
 
   return (
     <div style={{ width: "100%" }}>
       <Grid className="gap-2 p-10 h-[75vh] w-full">
-        <CreateUser
+        <CreateUser userID={userID} accessToken={accessToken} />
-            userID={userID}
+        <Card className="w-full mx-auto flex-auto overflow-y-auto max-h-[50vh] mb-4">
-            accessToken={accessToken}
+          <TabGroup>
-          />
+            <TabList variant="line" defaultValue="1">
-      <Card>
+              <Tab value="1">Key Owners</Tab>
+              <Tab value="2">End-Users</Tab>
+            </TabList>
+            <TabPanels>
+              <TabPanel>
                 <Table className="mt-5">
                   <TableHead>
                     <TableRow>
-              <TableCell><Title>User ID </Title></TableCell>
+                      <TableHeaderCell>User ID</TableHeaderCell>
-              <TableCell><Title>User Role</Title></TableCell>
+                      <TableHeaderCell>User Role</TableHeaderCell>
-              <TableCell><Title>User Models</Title></TableCell>
+                      <TableHeaderCell>User Models</TableHeaderCell>
-              <TableCell><Title>User Spend ($ USD)</Title></TableCell>
+                      <TableHeaderCell>User Spend ($ USD)</TableHeaderCell>
-              <TableCell><Title>User Max Budget  ($ USD)</Title></TableCell>
+                      <TableHeaderCell>User Max Budget ($ USD)</TableHeaderCell>
                     </TableRow>
                   </TableHead>
                   <TableBody>
                     {userData.map((user: any) => (
                       <TableRow key={user.user_id}>
-                <TableCell><Title>{user.user_id}</Title></TableCell>
+                        <TableCell>{user.user_id}</TableCell>
-                <TableCell><Title>{user.user_role ? user.user_role : "app_user"}</Title></TableCell>
+                        <TableCell>
-                <TableCell><Title>{user.models && user.models.length > 0 ? user.models : "All Models"}</Title></TableCell>
+                          {user.user_role ? user.user_role : "app_owner"}
-                <TableCell><Title>{user.spend ? user.spend : 0}</Title></TableCell>
+                        </TableCell>
-                <TableCell><Title>{user.max_budget ? user.max_budget : "Unlimited"}</Title></TableCell>
+                        <TableCell>
-
+                          {user.models && user.models.length > 0
+                            ? user.models
+                            : "All Models"}
+                        </TableCell>
+                        <TableCell>{user.spend ? user.spend : 0}</TableCell>
+                        <TableCell>
+                          {user.max_budget ? user.max_budget : "Unlimited"}
+                        </TableCell>
                       </TableRow>
                     ))}
                   </TableBody>
                 </Table>
+              </TabPanel>
+              <TabPanel>
+                <Table>
+                  <TableHead>
+                    <TableRow>
+                      <TableHeaderCell>End User</TableHeaderCell>
+                      <TableHeaderCell>Spend</TableHeaderCell>
+                      <TableHeaderCell>Total Events</TableHeaderCell>
+                    </TableRow>
+                  </TableHead>
+
+                  <TableBody>
+                    {endUsers?.map((user: any, index: number) => (
+                      <TableRow key={index}>
+                        <TableCell>{user.end_user}</TableCell>
+                        <TableCell>{user.total_spend}</TableCell>
+                        <TableCell>{user.total_events}</TableCell>
+                      </TableRow>
+                    ))}
+                  </TableBody>
+                </Table>
+              </TabPanel>
+            </TabPanels>
+          </TabGroup>
         </Card>
+        {renderPagination()}
       </Grid>
     </div>
   );