Merge branch 'main' into litellm_cleanup_traceback

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

@@ -41,7 +41,9 @@ litellm_settings:
 **Step 3**: Set required env variables for logging to langfuse
 ```shell
 export LANGFUSE_PUBLIC_KEY="pk_kk"
-export LANGFUSE_SECRET_KEY="sk_ss
+export LANGFUSE_SECRET_KEY="sk_ss"
+# Optional, defaults to https://cloud.langfuse.com
+export LANGFUSE_HOST="https://xxx.langfuse.com"
 ```
 
 **Step 4**: Start the proxy, make a test request

docs/my-website/docs/scheduler.md

@@ -101,3 +101,75 @@ print(response)
 
 </TabItem>
 </Tabs>
+
+## Advanced - Redis Caching 
+
+Use redis caching to do request prioritization across multiple instances of LiteLLM. 
+
+### SDK 
+```python
+from litellm import Router
+
+router = Router(
+    model_list=[
+        {
+            "model_name": "gpt-3.5-turbo",
+            "litellm_params": {
+                "model": "gpt-3.5-turbo",
+                "mock_response": "Hello world this is Macintosh!", # fakes the LLM API call
+                "rpm": 1,
+            },
+        },
+    ],
+    ### REDIS PARAMS ###
+    redis_host=os.environ["REDIS_HOST"], 
+    redis_password=os.environ["REDIS_PASSWORD"], 
+    redis_port=os.environ["REDIS_PORT"], 
+)
+
+try:
+    _response = await router.schedule_acompletion( # 👈 ADDS TO QUEUE + POLLS + MAKES CALL
+        model="gpt-3.5-turbo",
+        messages=[{"role": "user", "content": "Hey!"}],
+        priority=0, # 👈 LOWER IS BETTER
+    )
+except Exception as e:
+    print("didn't make request")
+```
+
+### PROXY 
+
+```yaml
+model_list:
+    - model_name: gpt-3.5-turbo-fake-model
+      litellm_params:
+        model: gpt-3.5-turbo
+        mock_response: "hello world!" 
+        api_key: my-good-key
+
+router_settings:
+    redis_host; os.environ/REDIS_HOST
+    redis_password: os.environ/REDIS_PASSWORD
+    redis_port: os.environ/REDIS_PORT
+```
+
+```bash
+$ litellm --config /path/to/config.yaml 
+
+# RUNNING on http://0.0.0.0:4000s
+```
+
+```bash
+curl -X POST 'http://localhost:4000/queue/chat/completions' \
+-H 'Content-Type: application/json' \
+-H 'Authorization: Bearer sk-1234' \
+-D '{
+    "model": "gpt-3.5-turbo-fake-model",
+    "messages": [
+        {
+        "role": "user",
+        "content": "what is the meaning of the universe? 1234"
+        }],
+    "priority": 0 👈 SET VALUE HERE
+}'
+```

docs/my-website/package-lock.json

@@ -5975,9 +5975,9 @@
       }
     },
     "node_modules/caniuse-lite": {
-      "version": "1.0.30001519",
+      "version": "1.0.30001629",
-      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001519.tgz",
+      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001629.tgz",
-      "integrity": "sha512-0QHgqR+Jv4bxHMp8kZ1Kn8CH55OikjKJ6JmKkZYP1F3D7w+lnFXF70nG5eNfsZS89jadi5Ywy5UCSKLAglIRkg==",
+      "integrity": "sha512-c3dl911slnQhmxUIT4HhYzT7wnBK/XYpGnYLOj4nJBaRiw52Ibe7YxlDaAeRECvA786zCuExhxIUJ2K7nHMrBw==",
       "funding": [
         {
           "type": "opencollective",

litellm/integrations/langfuse.py

@@ -78,8 +78,17 @@ class LangFuseLogger:
         For example if you want to append your trace to an existing `trace_id` via header, send
         `headers: { ..., langfuse_existing_trace_id: your-existing-trace-id }` via proxy request.
         """
-        proxy_headers = litellm_params.get("proxy_server_request", {}).get(
+        if litellm_params is None:
-            "headers", {}
+            return metadata
+
+        if litellm_params.get("proxy_server_request") is None:
+            return metadata
+
+        if metadata is None:
+            metadata = {}
+
+        proxy_headers = (
+            litellm_params.get("proxy_server_request", {}).get("headers", {}) or {}
         )
 
         for metadata_param_key in proxy_headers:

litellm/llms/ollama.py

@@ -2,8 +2,9 @@ from itertools import chain
 import requests, types, time  # type: ignore
 import json, uuid
 import traceback
-from typing import Optional
+from typing import Optional, List
 import litellm
+from litellm.types.utils import ProviderField
 import httpx, aiohttp, asyncio  # type: ignore
 from .prompt_templates.factory import prompt_factory, custom_prompt
 from litellm import verbose_logger
@@ -126,6 +127,18 @@ class OllamaConfig:
             and v is not None
         }
     
+    def get_required_params(self) -> List[ProviderField]:
+        """For a given provider, return it's required fields with a description"""
+        return [
+            ProviderField(
+                field_name="base_url",
+                field_type="string",
+                field_description="Your Ollama API Base",
+                field_value="http://10.10.11.249:11434",
+            )
+        ]
+
+
     def get_supported_openai_params(
         self,
     ):

litellm/llms/vertex_ai.py

@@ -647,9 +647,9 @@ def completion(
 
         prompt = " ".join(
             [
-                message["content"]
+                message.get("content")
                 for message in messages
-                if isinstance(message["content"], str)
+                if isinstance(message.get("content", None), str)
             ]
         )
 

litellm/router.py

@@ -220,8 +220,6 @@ class Router:
             []
         )  # names of models under litellm_params. ex. azure/chatgpt-v-2
         self.deployment_latency_map = {}
-        ### SCHEDULER ###
-        self.scheduler = Scheduler(polling_interval=polling_interval)
         ### CACHING ###
         cache_type: Literal["local", "redis"] = "local"  # default to an in-memory cache
         redis_cache = None
@@ -259,6 +257,10 @@ class Router:
             redis_cache=redis_cache, in_memory_cache=InMemoryCache()
         )  # use a dual cache (Redis+In-Memory) for tracking cooldowns, usage, etc.
 
+        ### SCHEDULER ###
+        self.scheduler = Scheduler(
+            polling_interval=polling_interval, redis_cache=redis_cache
+        )
         self.default_deployment = None  # use this to track the users default deployment, when they want to use model = *
         self.default_max_parallel_requests = default_max_parallel_requests
 

litellm/scheduler.py

@@ -1,13 +1,14 @@
-import heapq, time
+import heapq
 from pydantic import BaseModel
 from typing import Optional
 import enum
-from litellm.caching import DualCache
+from litellm.caching import DualCache, RedisCache
 from litellm import print_verbose
 
 
 class SchedulerCacheKeys(enum.Enum):
     queue = "scheduler:queue"
+    default_in_memory_ttl = 5  # cache queue in-memory for 5s when redis cache available
 
 
 class DefaultPriorities(enum.Enum):
@@ -25,18 +26,24 @@ class FlowItem(BaseModel):
 class Scheduler:
     cache: DualCache
 
-    def __init__(self, polling_interval: Optional[float] = None):
+    def __init__(
+        self,
+        polling_interval: Optional[float] = None,
+        redis_cache: Optional[RedisCache] = None,
+    ):
         """
         polling_interval: float or null - frequency of polling queue. Default is 3ms.
         """
         self.queue: list = []
-        self.cache = DualCache()
+        default_in_memory_ttl: Optional[float] = None
+        if redis_cache is not None:
+            # if redis-cache available frequently poll that instead of using in-memory.
+            default_in_memory_ttl = SchedulerCacheKeys.default_in_memory_ttl.value
+        self.cache = DualCache(
+            redis_cache=redis_cache, default_in_memory_ttl=default_in_memory_ttl
+        )
         self.polling_interval = polling_interval or 0.03  # default to 3ms
 
-    def update_variables(self, cache: Optional[DualCache] = None):
-        if cache is not None:
-            self.cache = cache
-
     async def add_request(self, request: FlowItem):
         # We use the priority directly, as lower values indicate higher priority
         # get the queue

litellm/utils.py

@@ -7355,6 +7355,10 @@ def get_provider_fields(custom_llm_provider: str) -> List[ProviderField]:
 
     if custom_llm_provider == "databricks":
         return litellm.DatabricksConfig().get_required_params()
+    
+    elif custom_llm_provider == "ollama":
+        return litellm.OllamaConfig().get_required_params()
+    
     else:
         return []
 

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "aiohttp"
@@ -2114,6 +2114,7 @@ files = [
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
     {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
+    {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
     {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
     {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
     {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@@ -2121,8 +2122,15 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
     {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
+    {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
     {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
+    {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
+    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
+    {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
+    {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
     {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
     {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@@ -2139,6 +2147,7 @@ files = [
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
     {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
+    {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
     {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
     {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
     {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@@ -2146,6 +2155,7 @@ files = [
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
     {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
+    {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
     {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
     {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@@ -3140,4 +3150,4 @@ proxy = ["PyJWT", "apscheduler", "backoff", "cryptography", "fastapi", "fastapi-
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0, !=3.9.7"
-content-hash = "a54d969a1a707413e7cd3ce869d14ef73dd41bb9d36ebf0fb878d9e929bc15b3"
+content-hash = "6a37992b63b11d254f5f40687bd96898b1d9515728f663f30dcc81c4ef8df7b7"

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

@@ -145,6 +145,7 @@ enum Providers {
   OpenAI_Compatible = "OpenAI-Compatible Endpoints (Groq, Together AI, Mistral AI, etc.)",
   Vertex_AI = "Vertex AI (Anthropic, Gemini, etc.)",
   Databricks = "Databricks",
+  Ollama = "Ollama",
 }
 
 const provider_map: Record<string, string> = {
@@ -156,6 +157,7 @@ const provider_map: Record<string, string> = {
   OpenAI_Compatible: "openai",
   Vertex_AI: "vertex_ai",
   Databricks: "databricks",
+  Ollama: "ollama",
 };
 
 const retry_policy_map: Record<string, string> = {
@@ -1747,6 +1749,7 @@ const ModelDashboard: React.FC<ModelDashboardProps> = ({
                     )}
                   {selectedProvider != Providers.Bedrock &&
                     selectedProvider != Providers.Vertex_AI &&
+                    selectedProvider != Providers.Ollama &&
                     (dynamicProviderForm === undefined ||
                       dynamicProviderForm.fields.length == 0) && (
                       <Form.Item