Merge branch 'main' into main

.circleci/requirements.txt

@@ -3,3 +3,4 @@ openai
 python-dotenv
 openai
 tiktoken
+importlib_metadata

.gitignore

@@ -2,3 +2,4 @@
 .env
 litellm_uuid.txt
 __pycache__/
+bun.lockb

README.md

@@ -3,7 +3,6 @@
 [![PyPI Version](https://img.shields.io/badge/stable%20version-v0.1.424-blue?color=green&link=https://pypi.org/project/litellm/0.1.1/)](https://pypi.org/project/litellm/0.1.1/)
 [![CircleCI](https://dl.circleci.com/status-badge/img/gh/BerriAI/litellm/tree/main.svg?style=svg)](https://dl.circleci.com/status-badge/redirect/gh/BerriAI/litellm/tree/main)
 ![Downloads](https://img.shields.io/pypi/dm/litellm)
-[![litellm](https://img.shields.io/badge/%20%F0%9F%9A%85%20liteLLM-OpenAI%7CAzure%7CAnthropic%7CPalm%7CCohere%7CReplicate%7CHugging%20Face-blue?color=green)](https://github.com/BerriAI/litellm)
 
 [![](https://dcbadge.vercel.app/api/server/wuPM9dRgDw)](https://discord.gg/wuPM9dRgDw)
 
@@ -12,10 +11,11 @@ a light package to simplify calling OpenAI, Azure, Cohere, Anthropic, Huggingfac
 - guarantees [consistent output](https://litellm.readthedocs.io/en/latest/output/), text responses will always be available at `['choices'][0]['message']['content']`
 - exception mapping - common exceptions across providers are mapped to the [OpenAI exception types](https://help.openai.com/en/articles/6897213-openai-library-error-types-guidance)
 # usage
-<a href='https://docs.litellm.ai/docs/completion/supported' target="_blank"><img alt='None' src='https://img.shields.io/badge/Supported_LLMs-100000?style=for-the-badge&logo=None&logoColor=000000&labelColor=000000&color=8400EA'/></a>
+<a href='https://docs.litellm.ai/docs/completion/supported' target="_blank"><img alt='None' src='https://img.shields.io/badge/100+_Supported_LLMs_liteLLM-100000?style=for-the-badge&logo=None&logoColor=000000&labelColor=000000&color=8400EA'/></a>
 
-Demo - https://litellm.ai/playground \
+Demo - https://litellm.ai/playground  
-Read the docs - https://docs.litellm.ai/docs/
+Docs - https://docs.litellm.ai/docs/  
+**Free** Dashboard - https://docs.litellm.ai/docs/debugging/hosted_debugging
 
 ## quick start
 ```

cookbook/liteLLM_A121_Jurrasic_example.ipynb

@@ -0,0 +1,251 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# LiteLLM A121 Tutorial\n",
+        "\n",
+        "This walks through using A121 Jurassic models\n",
+        "* j2-light\n",
+        "* j2-mid\n",
+        "* j2-ultra"
+      ],
+      "metadata": {
+        "id": "LeFYo8iqcn5g"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GslPQFmaZsp-"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install litellm"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from litellm import completion\n",
+        "import os"
+      ],
+      "metadata": {
+        "id": "P3cKiqURZx7P"
+      },
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Set A121 Keys\n",
+        "You can get a free key from https://studio.ai21.com/account/api-key"
+      ],
+      "metadata": {
+        "id": "tmTvA1_GaNU4"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "os.environ[\"AI21_API_KEY\"] = \"\""
+      ],
+      "metadata": {
+        "id": "_xX8LmxAZ2vp"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# A121 Supported Models:\n",
+        "https://studio.ai21.com/foundation-models"
+      ],
+      "metadata": {
+        "id": "Fx5ZfJTLbF0A"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## J2-light Call"
+      ],
+      "metadata": {
+        "id": "H0tl-0Z3bDaL"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages = [{ \"content\": \"Hello, how are you?\",\"role\": \"user\"}]\n",
+        "response = completion(model=\"j2-light\", messages=messages)\n",
+        "response"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "DZnApsJUZ_I2",
+        "outputId": "b5707cbe-f67c-47f7-bac5-a7b8af1ba815"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<ModelResponse at 0x7b2c2902e610> JSON: {\n",
+              "  \"choices\": [\n",
+              "    {\n",
+              "      \"finish_reason\": \"stop\",\n",
+              "      \"index\": 0,\n",
+              "      \"message\": {\n",
+              "        \"content\": \" However, I have an important question to ask you\\nMy name is X, and I was wondering if you would be willing to help me.\",\n",
+              "        \"role\": \"assistant\"\n",
+              "      }\n",
+              "    }\n",
+              "  ],\n",
+              "  \"created\": 1692761063.5189915,\n",
+              "  \"model\": \"j2-light\",\n",
+              "  \"usage\": {\n",
+              "    \"prompt_tokens\": null,\n",
+              "    \"completion_tokens\": null,\n",
+              "    \"total_tokens\": null\n",
+              "  }\n",
+              "}"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 6
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# J2-Mid"
+      ],
+      "metadata": {
+        "id": "wCcnrYnnbMQA"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages = [{ \"content\": \"what model are you\",\"role\": \"user\"}]\n",
+        "response = completion(model=\"j2-mid\", messages=messages)\n",
+        "response"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "-5Sxf4blaeEl",
+        "outputId": "6264a5e8-16d6-44a3-e167-9e0c59b6dbc4"
+      },
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<ModelResponse at 0x7b2c2902f6a0> JSON: {\n",
+              "  \"choices\": [\n",
+              "    {\n",
+              "      \"finish_reason\": \"stop\",\n",
+              "      \"index\": 0,\n",
+              "      \"message\": {\n",
+              "        \"content\": \"\\nplease choose the model from the list below\\nModel view in Tekla Structures\",\n",
+              "        \"role\": \"assistant\"\n",
+              "      }\n",
+              "    }\n",
+              "  ],\n",
+              "  \"created\": 1692761140.0017524,\n",
+              "  \"model\": \"j2-mid\",\n",
+              "  \"usage\": {\n",
+              "    \"prompt_tokens\": null,\n",
+              "    \"completion_tokens\": null,\n",
+              "    \"total_tokens\": null\n",
+              "  }\n",
+              "}"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 7
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# J2-Ultra"
+      ],
+      "metadata": {
+        "id": "wDARpjxtbUcg"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "messages = [{ \"content\": \"what model are you\",\"role\": \"user\"}]\n",
+        "response = completion(model=\"j2-ultra\", messages=messages)\n",
+        "response"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "i228xwsYbSYo",
+        "outputId": "3765ac56-5a9b-442e-b357-2e346d02e1df"
+      },
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<ModelResponse at 0x7b2c28fd4090> JSON: {\n",
+              "  \"choices\": [\n",
+              "    {\n",
+              "      \"finish_reason\": \"stop\",\n",
+              "      \"index\": 0,\n",
+              "      \"message\": {\n",
+              "        \"content\": \"\\nI am not a specific model, but I can provide information and assistance based on my training data. Please let me know if there is anything you\",\n",
+              "        \"role\": \"assistant\"\n",
+              "      }\n",
+              "    }\n",
+              "  ],\n",
+              "  \"created\": 1692761157.8675153,\n",
+              "  \"model\": \"j2-ultra\",\n",
+              "  \"usage\": {\n",
+              "    \"prompt_tokens\": null,\n",
+              "    \"completion_tokens\": null,\n",
+              "    \"total_tokens\": null\n",
+              "  }\n",
+              "}"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 8
+        }
+      ]
+    }
+  ]
+}

docs/my-website/docs/completion/supported.md

@@ -77,6 +77,22 @@ Here are some examples of supported models:
 | [bigcode/starcoder](https://huggingface.co/bigcode/starcoder)                           | `completion(model="bigcode/starcoder", messages=messages, custom_llm_provider="huggingface")`          | `os.environ['HUGGINGFACE_API_KEY']`       |
 | [google/flan-t5-xxl](https://huggingface.co/google/flan-t5-xxl)                         | `completion(model="google/flan-t5-xxl", messages=messages, custom_llm_provider="huggingface")`         | `os.environ['HUGGINGFACE_API_KEY']`       |
 | [google/flan-t5-large](https://huggingface.co/google/flan-t5-large)                     | `completion(model="google/flan-t5-large", messages=messages, custom_llm_provider="huggingface")`       | `os.environ['HUGGINGFACE_API_KEY']`       |
+
+### Replicate Models
+liteLLM supports all replicate LLMs. For replicate models ensure to add a `replicate` prefix to the `model` arg. liteLLM detects it using this arg. 
+Below are examples on how to call replicate LLMs using liteLLM 
+
+Model Name                  | Function Call                                                  | Required OS Variables                |
+-----------------------------|----------------------------------------------------------------|--------------------------------------|
+ replicate/llama-2-70b-chat | `completion('replicate/replicate/llama-2-70b-chat', messages)` | `os.environ['REPLICATE_API_KEY']`    |
+ a16z-infra/llama-2-13b-chat| `completion('replicate/a16z-infra/llama-2-13b-chat', messages)`| `os.environ['REPLICATE_API_KEY']`    |
+ joehoover/instructblip-vicuna13b | `completion('replicate/joehoover/instructblip-vicuna13b', messages)` | `os.environ['REPLICATE_API_KEY']` |
+ replicate/dolly-v2-12b     | `completion('replicate/replicate/dolly-v2-12b', messages)`     | `os.environ['REPLICATE_API_KEY']`    |
+ a16z-infra/llama-2-7b-chat | `completion('replicate/a16z-infra/llama-2-7b-chat', messages)` | `os.environ['REPLICATE_API_KEY']`    |
+ replicate/vicuna-13b       | `completion('replicate/replicate/vicuna-13b', messages)`       | `os.environ['REPLICATE_API_KEY']`    |
+ daanelson/flan-t5-large    | `completion('replicate/daanelson/flan-t5-large', messages)`    | `os.environ['REPLICATE_API_KEY']`    |
+ replit/replit-code-v1-3b   | `completion('replicate/replit/replit-code-v1-3b', messages)`   | `os.environ['REPLICATE_API_KEY']`    |
+
 ### AI21 Models
 
 | Model Name       | Function Call                              | Required OS Variables                |
@@ -112,9 +128,9 @@ Example Baseten Usage - Note: liteLLM supports all models deployed on Basten
 
 | Model Name       | Function Call                                  | Required OS Variables              |
 |------------------|--------------------------------------------|------------------------------------|
-| Falcon 7B        | `completion(model='<your model version id>', messages=messages, custom_llm_provider="baseten")`         | `os.environ['BASETEN_API_KEY']`     |
+| Falcon 7B        | `completion(model='baseten/qvv0xeq', messages=messages)`         | `os.environ['BASETEN_API_KEY']`     |
-| Wizard LM        | `completion(model='<your model version id>', messages=messages, custom_llm_provider="baseten")`         | `os.environ['BASETEN_API_KEY']`     |
+| Wizard LM        | `completion(model='baseten/q841o8w', messages=messages)`         | `os.environ['BASETEN_API_KEY']`     |
-| MPT 7B Base      | `completion(model='<your model version id>', messages=messages, custom_llm_provider="baseten")`         | `os.environ['BASETEN_API_KEY']`     |
+| MPT 7B Base      | `completion(model='baseten/31dxrj3', messages=messages)`         | `os.environ['BASETEN_API_KEY']`     |
 
 
 ### OpenRouter Completion Models

docs/my-website/docs/debugging/hosted_debugging.md

@@ -0,0 +1,40 @@
+import Image from '@theme/IdealImage';
+
+# Debugging Dashboard
+LiteLLM offers a free UI to debug your calls + add new models at (https://admin.litellm.ai/). This is useful if you're testing your LiteLLM server and need to see if the API calls were made successfully **or** want to add new models without going into code. 
+
+**Needs litellm>=0.1.438***
+
+## Setup
+
+Once created, your dashboard is viewable at - `admin.litellm.ai/<your_email>` [👋 Tell us if you need better privacy controls](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version?month=2023-08)
+
+You can set your user email in 2 ways.  
+- By setting it on the module - `litellm.email=<your_email>`.
+- By setting it as an environment variable - `os.environ["LITELLM_EMAIL"] = "your_email"`.
+
+<Image img={require('../../img/dashboard.png')} alt="Dashboard" />
+
+See our live dashboard 👉 [admin.litellm.ai](https://admin.litellm.ai/)
+
+
+## Example Usage
+
+```
+ import litellm
+ from litellm import embedding, completion
+ 
+ ## Set your email
+ litellm.email = "test_email@test.com"
+
+ user_message = "Hello, how are you?"
+ messages = [{ "content": user_message,"role": "user"}]
+
+
+ # openai call
+ response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
+
+ # bad request call
+ response = completion(model="chatgpt-test", messages=[{"role": "user", "content": "Hi 👋 - i'm a bad request"}])
+```
+

docs/my-website/docs/debugging/local_debugging.md

@@ -55,3 +55,9 @@ response = completion(model="gpt-3.5-turbo", messages=messages, logger_fn=my_cus
 # cohere call
 response = completion("command-nightly", messages, logger_fn=my_custom_logging_fn)
 ```
+
+## Still Seeing Issues? 
+
+Text us @ +17708783106 or Join the [Discord](https://discord.com/invite/wuPM9dRgDw). 
+
+We promise to help you in `lite`ning speed ❤️

docs/my-website/docs/tutorials/TogetherAI_liteLLM.md

@@ -1,4 +1,4 @@
-## liteLLM Together AI Tutorial
+# liteLLM Together AI Tutorial
 https://together.ai/
 
 

docs/my-website/docs/tutorials/debugging_tutorial.md

@@ -1,32 +0,0 @@
-# Debugging UI Tutorial
-LiteLLM offers a free hosted debugger UI for your api calls. Useful if you're testing your LiteLLM server and need to see if the API calls were made successfully.
-
-You can enable this setting `lite_debugger` as a callback. 
-
-## Example Usage
-
-```
- import litellm
- from litellm import embedding, completion
-
- litellm.input_callback = ["lite_debugger"]
- litellm.success_callback = ["lite_debugger"]
- litellm.failure_callback = ["lite_debugger"]
-
- litellm.set_verbose = True
-
- user_message = "Hello, how are you?"
- messages = [{ "content": user_message,"role": "user"}]
-
-
- # openai call
- response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
-
- # bad request call
- response = completion(model="chatgpt-test", messages=[{"role": "user", "content": "Hi 👋 - i'm a bad request"}])
-
-```
-
-## Requirements
-
-## How to see the UI

docs/my-website/docs/tutorials/fallbacks.md

@@ -0,0 +1,41 @@
+# Using completion() with Fallbacks for Reliability
+
+This tutorial demonstrates how to employ the `completion()` function with model fallbacks to ensure reliability. LLM APIs can be unstable, completion() with fallbacks ensures you'll always get a response from your calls
+
+## Usage 
+To use fallback models with `completion()`, specify a list of models in the `fallbacks` parameter. 
+
+```python
+response = completion(model="bad-model", messages=messages, fallbacks=["gpt-3.5-turbo" "command-nightly"])
+```
+
+### Output from calls
+```
+Completion with 'bad-model': got exception Unable to map your input to a model. Check your input - {'model': 'bad-model'
+
+
+
+completion call gpt-3.5-turbo
+{
+  "id": "chatcmpl-7qTmVRuO3m3gIBg4aTmAumV1TmQhB",
+  "object": "chat.completion",
+  "created": 1692741891,
+  "model": "gpt-3.5-turbo-0613",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "I apologize, but as an AI, I do not have the capability to provide real-time weather updates. However, you can easily check the current weather in San Francisco by using a search engine or checking a weather website or app."
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 16,
+    "completion_tokens": 46,
+    "total_tokens": 62
+  }
+}
+
+```

docs/my-website/docs/tutorials/finetuned_chat_gpt.md

@@ -0,0 +1,22 @@
+# Using Fine-Tuned gpt-3.5-turbo
+LiteLLM allows you to call `completion` with your fine-tuned gpt-3.5-turbo models
+If you're trying to create your custom finetuned gpt-3.5-turbo model following along on this tutorial: https://platform.openai.com/docs/guides/fine-tuning/preparing-your-dataset
+
+Once you've created your fine tuned model, you can call it with `completion()` 
+
+## Usage
+```python
+import os
+from litellm import completion
+# set your OPENAI key in your .env as "OPENAI_API_KEY"
+
+response = completion(
+  model="ft:gpt-3.5-turbo:my-org:custom_suffix:id",
+  messages=[
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Hello!"}
+  ]
+)
+
+print(response.choices[0].message)
+```

docs/my-website/docs/tutorials/react_test.js

@@ -1,21 +0,0 @@
-import React from 'react';
-import Layout from '@theme/Layout';
-
-export default function Hello() {
-  return (
-    <Layout title="Hello" description="Hello React Page">
-      <div
-        style={{
-          display: 'flex',
-          justifyContent: 'center',
-          alignItems: 'center',
-          height: '50vh',
-          fontSize: '20px',
-        }}>
-        <p>
-          Edit <code>pages/helloReact.js</code> and save to reload.
-        </p>
-      </div>
-    </Layout>
-  );
-}

docs/my-website/docusaurus.config.js

@@ -27,6 +27,22 @@ const config = {
     locales: ['en'],
   },
 
+  plugins: [
+    [
+      '@docusaurus/plugin-ideal-image',
+      {
+        quality: 70,
+        max: 1030, // max resized image's size.
+        min: 640, // min resized image's size. if original is lower, use that size.
+        steps: 2, // the max number of images generated between min and max (inclusive)
+        disableInDev: false,
+      },
+    ],
+    [ require.resolve('docusaurus-lunr-search'), {
+      languages: ['en'] // language codes
+    }]
+  ],
+
   presets: [
     [
       'classic',
@@ -72,7 +88,7 @@ const config = {
             items: [
               {
                 label: 'Tutorial',
-                to: '/docs/intro',
+                to: '/docs/index',
               },
             ],
           },

docs/my-website/package-lock.json

@@ -9,12 +9,14 @@
       "version": "0.0.0",
       "dependencies": {
         "@docusaurus/core": "2.4.1",
+        "@docusaurus/plugin-ideal-image": "^2.4.1",
         "@docusaurus/preset-classic": "2.4.1",
         "@mdx-js/react": "^1.6.22",
         "clsx": "^1.2.1",
         "prism-react-renderer": "^1.3.5",
         "react": "^17.0.2",
-        "react-dom": "^17.0.2"
+        "react-dom": "^17.0.2",
+        "uuid": "^9.0.0"
       },
       "devDependencies": {
         "@docusaurus/module-type-aliases": "2.4.1"
@@ -2268,6 +2270,21 @@
         "node": ">=16.14"
       }
     },
+    "node_modules/@docusaurus/lqip-loader": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/@docusaurus/lqip-loader/-/lqip-loader-2.4.1.tgz",
+      "integrity": "sha512-XJ0z/xSx5HtAQ+/xBoAiRZ7DY9zEP6IImAKlAk6RxuFzyB4HT8eINWN+LwLnOsTh5boIj37JCX+T76bH0ieULA==",
+      "dependencies": {
+        "@docusaurus/logger": "2.4.1",
+        "file-loader": "^6.2.0",
+        "lodash": "^4.17.21",
+        "sharp": "^0.30.7",
+        "tslib": "^2.4.0"
+      },
+      "engines": {
+        "node": ">=16.14"
+      }
+    },
     "node_modules/@docusaurus/mdx-loader": {
       "version": "2.4.1",
       "resolved": "https://registry.npmjs.org/@docusaurus/mdx-loader/-/mdx-loader-2.4.1.tgz",
@@ -2474,6 +2491,37 @@
         "react-dom": "^16.8.4 || ^17.0.0"
       }
     },
+    "node_modules/@docusaurus/plugin-ideal-image": {
+      "version": "2.4.1",
+      "resolved": "https://registry.npmjs.org/@docusaurus/plugin-ideal-image/-/plugin-ideal-image-2.4.1.tgz",
+      "integrity": "sha512-jxvgCGPmHxdae2Y2uskzxIbMCA4WLTfzkufsLbD4mEAjCRIkt6yzux6q5kqKTrO+AxzpANVcJNGmaBtKZGv5aw==",
+      "dependencies": {
+        "@docusaurus/core": "2.4.1",
+        "@docusaurus/lqip-loader": "2.4.1",
+        "@docusaurus/responsive-loader": "^1.7.0",
+        "@docusaurus/theme-translations": "2.4.1",
+        "@docusaurus/types": "2.4.1",
+        "@docusaurus/utils-validation": "2.4.1",
+        "@endiliey/react-ideal-image": "^0.0.11",
+        "react-waypoint": "^10.3.0",
+        "sharp": "^0.30.7",
+        "tslib": "^2.4.0",
+        "webpack": "^5.73.0"
+      },
+      "engines": {
+        "node": ">=16.14"
+      },
+      "peerDependencies": {
+        "jimp": "*",
+        "react": "^16.8.4 || ^17.0.0",
+        "react-dom": "^16.8.4 || ^17.0.0"
+      },
+      "peerDependenciesMeta": {
+        "jimp": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/@docusaurus/plugin-sitemap": {
       "version": "2.4.1",
       "resolved": "https://registry.npmjs.org/@docusaurus/plugin-sitemap/-/plugin-sitemap-2.4.1.tgz",
@@ -2536,6 +2584,29 @@
         "react": "*"
       }
     },
+    "node_modules/@docusaurus/responsive-loader": {
+      "version": "1.7.0",
+      "resolved": "https://registry.npmjs.org/@docusaurus/responsive-loader/-/responsive-loader-1.7.0.tgz",
+      "integrity": "sha512-N0cWuVqTRXRvkBxeMQcy/OF2l7GN8rmni5EzR3HpwR+iU2ckYPnziceojcxvvxQ5NqZg1QfEW0tycQgHp+e+Nw==",
+      "dependencies": {
+        "loader-utils": "^2.0.0"
+      },
+      "engines": {
+        "node": ">=12"
+      },
+      "peerDependencies": {
+        "jimp": "*",
+        "sharp": "*"
+      },
+      "peerDependenciesMeta": {
+        "jimp": {
+          "optional": true
+        },
+        "sharp": {
+          "optional": true
+        }
+      }
+    },
     "node_modules/@docusaurus/theme-classic": {
       "version": "2.4.1",
       "resolved": "https://registry.npmjs.org/@docusaurus/theme-classic/-/theme-classic-2.4.1.tgz",
@@ -2734,6 +2805,20 @@
         "node": ">=16.14"
       }
     },
+    "node_modules/@endiliey/react-ideal-image": {
+      "version": "0.0.11",
+      "resolved": "https://registry.npmjs.org/@endiliey/react-ideal-image/-/react-ideal-image-0.0.11.tgz",
+      "integrity": "sha512-QxMjt/Gvur/gLxSoCy7VIyGGGrGmDN+VHcXkN3R2ApoWX0EYUE+hMgPHSW/PV6VVebZ1Nd4t2UnGRBDihu16JQ==",
+      "engines": {
+        "node": ">= 8.9.0",
+        "npm": "> 3"
+      },
+      "peerDependencies": {
+        "prop-types": ">=15",
+        "react": ">=0.14.x",
+        "react-waypoint": ">=9.0.2"
+      }
+    },
     "node_modules/@hapi/hoek": {
       "version": "9.3.0",
       "resolved": "https://registry.npmjs.org/@hapi/hoek/-/hoek-9.3.0.tgz",
@@ -4180,6 +4265,25 @@
       "resolved": "https://registry.npmjs.org/base16/-/base16-1.0.0.tgz",
       "integrity": "sha512-pNdYkNPiJUnEhnfXV56+sQy8+AaPcG3POZAUnwr4EeqCUZFz4u2PePbo3e5Gj4ziYPCWGUZT9RHisvJKnwFuBQ=="
     },
+    "node_modules/base64-js": {
+      "version": "1.5.1",
+      "resolved": "https://registry.npmjs.org/base64-js/-/base64-js-1.5.1.tgz",
+      "integrity": "sha512-AKpaYlHn8t4SVbOHCy+b5+KKgvR4vrsD8vbvrbiQJps7fKDTkjkDry6ji0rUJjC0kzbNePLwzxq8iypo41qeWA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ]
+    },
     "node_modules/batch": {
       "version": "0.6.1",
       "resolved": "https://registry.npmjs.org/batch/-/batch-0.6.1.tgz",
@@ -4201,6 +4305,16 @@
         "node": ">=8"
       }
     },
+    "node_modules/bl": {
+      "version": "4.1.0",
+      "resolved": "https://registry.npmjs.org/bl/-/bl-4.1.0.tgz",
+      "integrity": "sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==",
+      "dependencies": {
+        "buffer": "^5.5.0",
+        "inherits": "^2.0.4",
+        "readable-stream": "^3.4.0"
+      }
+    },
     "node_modules/body-parser": {
       "version": "1.20.1",
       "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-1.20.1.tgz",
@@ -4333,6 +4447,29 @@
         "node": "^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7"
       }
     },
+    "node_modules/buffer": {
+      "version": "5.7.1",
+      "resolved": "https://registry.npmjs.org/buffer/-/buffer-5.7.1.tgz",
+      "integrity": "sha512-EHcyIPBQ4BSGlvjB16k5KgAJ27CIsHY/2JBmCRReo48y9rQ3MaUzWX3KVlBa4U7MyX02HdVj0K7C3WaB3ju7FQ==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "dependencies": {
+        "base64-js": "^1.3.1",
+        "ieee754": "^1.1.13"
+      }
+    },
     "node_modules/buffer-from": {
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/buffer-from/-/buffer-from-1.1.2.tgz",
@@ -4584,6 +4721,11 @@
         "fsevents": "~2.3.2"
       }
     },
+    "node_modules/chownr": {
+      "version": "1.1.4",
+      "resolved": "https://registry.npmjs.org/chownr/-/chownr-1.1.4.tgz",
+      "integrity": "sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg=="
+    },
     "node_modules/chrome-trace-event": {
       "version": "1.0.3",
       "resolved": "https://registry.npmjs.org/chrome-trace-event/-/chrome-trace-event-1.0.3.tgz",
@@ -4709,6 +4851,18 @@
         "url": "https://github.com/sponsors/wooorm"
       }
     },
+    "node_modules/color": {
+      "version": "4.2.3",
+      "resolved": "https://registry.npmjs.org/color/-/color-4.2.3.tgz",
+      "integrity": "sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==",
+      "dependencies": {
+        "color-convert": "^2.0.1",
+        "color-string": "^1.9.0"
+      },
+      "engines": {
+        "node": ">=12.5.0"
+      }
+    },
     "node_modules/color-convert": {
       "version": "2.0.1",
       "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz",
@@ -4725,6 +4879,15 @@
       "resolved": "https://registry.npmjs.org/color-name/-/color-name-1.1.4.tgz",
       "integrity": "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="
     },
+    "node_modules/color-string": {
+      "version": "1.9.1",
+      "resolved": "https://registry.npmjs.org/color-string/-/color-string-1.9.1.tgz",
+      "integrity": "sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==",
+      "dependencies": {
+        "color-name": "^1.0.0",
+        "simple-swizzle": "^0.2.2"
+      }
+    },
     "node_modules/colord": {
       "version": "2.9.3",
       "resolved": "https://registry.npmjs.org/colord/-/colord-2.9.3.tgz",
@@ -4853,6 +5016,11 @@
       "resolved": "https://registry.npmjs.org/consola/-/consola-2.15.3.tgz",
       "integrity": "sha512-9vAdYbHj6x2fLKC4+oPH0kFzY/orMZyG2Aj+kNylHxKGJ/Ed4dpNyAQYwJOdqO4zdM7XpVHmyejQDcQHrnuXbw=="
     },
+    "node_modules/consolidated-events": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/consolidated-events/-/consolidated-events-2.0.2.tgz",
+      "integrity": "sha512-2/uRVMdRypf5z/TW/ncD/66l75P5hH2vM/GR8Jf8HLc2xnfJtmina6F6du8+v4Z2vTrMo7jC+W1tmEEuuELgkQ=="
+    },
     "node_modules/content-disposition": {
       "version": "0.5.2",
       "resolved": "https://registry.npmjs.org/content-disposition/-/content-disposition-0.5.2.tgz",
@@ -5508,6 +5676,14 @@
         "url": "https://github.com/sponsors/wooorm"
       }
     },
+    "node_modules/detect-libc": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-2.0.2.tgz",
+      "integrity": "sha512-UX6sGumvvqSaXgdKGUsgZWqcUyIXZ/vZTrlRT/iobiKhGL0zL4d3osHj3uqllWJK+i+sixDS/3COVEOFbupFyw==",
+      "engines": {
+        "node": ">=8"
+      }
+    },
     "node_modules/detect-node": {
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/detect-node/-/detect-node-2.1.0.tgz",
@@ -5936,6 +6112,14 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/expand-template": {
+      "version": "2.0.3",
+      "resolved": "https://registry.npmjs.org/expand-template/-/expand-template-2.0.3.tgz",
+      "integrity": "sha512-XYfuKMvj4O35f/pOXLObndIRvyQ+/+6AhODh+OKWj9S9498pHHn/IMszH+gt0fBCRWMNfk1ZSp5x3AifmnI2vg==",
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/express": {
       "version": "4.18.2",
       "resolved": "https://registry.npmjs.org/express/-/express-4.18.2.tgz",
@@ -6389,6 +6573,11 @@
         "node": ">= 0.6"
       }
     },
+    "node_modules/fs-constants": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/fs-constants/-/fs-constants-1.0.0.tgz",
+      "integrity": "sha512-y6OAwoSIf7FyjMIv94u+b5rdheZEjzR63GTyZJm5qh4Bi+2YgwLCcI/fPFZkL5PSixOt6ZNKm+w+Hfp/Bciwow=="
+    },
     "node_modules/fs-extra": {
       "version": "10.1.0",
       "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-10.1.0.tgz",
@@ -6468,6 +6657,11 @@
         "node": ">=6"
       }
     },
+    "node_modules/github-from-package": {
+      "version": "0.0.0",
+      "resolved": "https://registry.npmjs.org/github-from-package/-/github-from-package-0.0.0.tgz",
+      "integrity": "sha512-SyHy3T1v2NUXn29OsWdxmK6RwHD+vkj3v8en8AOBZ1wBQ/hCAQ5bAQTD02kW4W9tUp/3Qh6J8r9EvntiyCmOOw=="
+    },
     "node_modules/github-slugger": {
       "version": "1.5.0",
       "resolved": "https://registry.npmjs.org/github-slugger/-/github-slugger-1.5.0.tgz",
@@ -7115,6 +7309,25 @@
         "postcss": "^8.1.0"
       }
     },
+    "node_modules/ieee754": {
+      "version": "1.2.1",
+      "resolved": "https://registry.npmjs.org/ieee754/-/ieee754-1.2.1.tgz",
+      "integrity": "sha512-dcyqhDvX1C46lXZcVqCpK+FtMRQVdIMN6/Df5js2zouUsqG7I6sFxitIC+7KYK29KdXOLHdu9zL4sFnoVQnqaA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ]
+    },
     "node_modules/ignore": {
       "version": "5.2.4",
       "resolved": "https://registry.npmjs.org/ignore/-/ignore-5.2.4.tgz",
@@ -8133,6 +8346,11 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/mkdirp-classic": {
+      "version": "0.5.3",
+      "resolved": "https://registry.npmjs.org/mkdirp-classic/-/mkdirp-classic-0.5.3.tgz",
+      "integrity": "sha512-gKLcREMhtuZRwRAfqP3RFW+TK4JqApVBtOIftVgjuABpAtpxhPGaDcfvbhNvD0B8iD1oUr/txX35NjcaY6Ns/A=="
+    },
     "node_modules/mrmime": {
       "version": "1.0.1",
       "resolved": "https://registry.npmjs.org/mrmime/-/mrmime-1.0.1.tgz",
@@ -8175,6 +8393,11 @@
         "node": "^10 || ^12 || ^13.7 || ^14 || >=15.0.1"
       }
     },
+    "node_modules/napi-build-utils": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/napi-build-utils/-/napi-build-utils-1.0.2.tgz",
+      "integrity": "sha512-ONmRUqK7zj7DWX0D9ADe03wbwOBZxNAfF20PlGfCWQcD3+/MakShIHrMqx9YwPTfxDdF1zLeL+RGZiR9kGMLdg=="
+    },
     "node_modules/negotiator": {
       "version": "0.6.3",
       "resolved": "https://registry.npmjs.org/negotiator/-/negotiator-0.6.3.tgz",
@@ -8197,6 +8420,22 @@
         "tslib": "^2.0.3"
       }
     },
+    "node_modules/node-abi": {
+      "version": "3.47.0",
+      "resolved": "https://registry.npmjs.org/node-abi/-/node-abi-3.47.0.tgz",
+      "integrity": "sha512-2s6B2CWZM//kPgwnuI0KrYwNjfdByE25zvAaEpq9IH4zcNsarH8Ihu/UuX6XMPEogDAxkuUFeZn60pXNHAqn3A==",
+      "dependencies": {
+        "semver": "^7.3.5"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/node-addon-api": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/node-addon-api/-/node-addon-api-5.1.0.tgz",
+      "integrity": "sha512-eh0GgfEkpnoWDq+VY8OyvYhFEzBk6jIYbRKdIlyTiAXIVJ8PyBaKb0rp7oDtoddbdoHWhq8wwr+XZ81F1rpNdA=="
+    },
     "node_modules/node-emoji": {
       "version": "1.11.0",
       "resolved": "https://registry.npmjs.org/node-emoji/-/node-emoji-1.11.0.tgz",
@@ -9303,6 +9542,31 @@
         "postcss": "^8.2.15"
       }
     },
+    "node_modules/prebuild-install": {
+      "version": "7.1.1",
+      "resolved": "https://registry.npmjs.org/prebuild-install/-/prebuild-install-7.1.1.tgz",
+      "integrity": "sha512-jAXscXWMcCK8GgCoHOfIr0ODh5ai8mj63L2nWrjuAgXE6tDyYGnx4/8o/rCgU+B4JSyZBKbeZqzhtwtC3ovxjw==",
+      "dependencies": {
+        "detect-libc": "^2.0.0",
+        "expand-template": "^2.0.3",
+        "github-from-package": "0.0.0",
+        "minimist": "^1.2.3",
+        "mkdirp-classic": "^0.5.3",
+        "napi-build-utils": "^1.0.1",
+        "node-abi": "^3.3.0",
+        "pump": "^3.0.0",
+        "rc": "^1.2.7",
+        "simple-get": "^4.0.0",
+        "tar-fs": "^2.0.0",
+        "tunnel-agent": "^0.6.0"
+      },
+      "bin": {
+        "prebuild-install": "bin.js"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
     "node_modules/prepend-http": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/prepend-http/-/prepend-http-2.0.0.tgz",
@@ -9820,6 +10084,25 @@
         "react": "^16.8.0 || ^17.0.0 || ^18.0.0"
       }
     },
+    "node_modules/react-waypoint": {
+      "version": "10.3.0",
+      "resolved": "https://registry.npmjs.org/react-waypoint/-/react-waypoint-10.3.0.tgz",
+      "integrity": "sha512-iF1y2c1BsoXuEGz08NoahaLFIGI9gTUAAOKip96HUmylRT6DUtpgoBPjk/Y8dfcFVmfVDvUzWjNXpZyKTOV0SQ==",
+      "dependencies": {
+        "@babel/runtime": "^7.12.5",
+        "consolidated-events": "^1.1.0 || ^2.0.0",
+        "prop-types": "^15.0.0",
+        "react-is": "^17.0.1 || ^18.0.0"
+      },
+      "peerDependencies": {
+        "react": "^15.3.0 || ^16.0.0 || ^17.0.0 || ^18.0.0"
+      }
+    },
+    "node_modules/react-waypoint/node_modules/react-is": {
+      "version": "18.2.0",
+      "resolved": "https://registry.npmjs.org/react-is/-/react-is-18.2.0.tgz",
+      "integrity": "sha512-xWGDIW6x921xtzPkhiULtthJHoJvBbF3q26fzloPCK0hsvxtPVelvftw3zjbHWSkR2km9Z+4uxbDDK/6Zw9B8w=="
+    },
     "node_modules/readable-stream": {
       "version": "3.6.2",
       "resolved": "https://registry.npmjs.org/readable-stream/-/readable-stream-3.6.2.tgz",
@@ -10745,6 +11028,28 @@
       "resolved": "https://registry.npmjs.org/shallowequal/-/shallowequal-1.1.0.tgz",
       "integrity": "sha512-y0m1JoUZSlPAjXVtPPW70aZWfIL/dSP7AFkRnniLCrK/8MDKog3TySTBmckD+RObVxH0v4Tox67+F14PdED2oQ=="
     },
+    "node_modules/sharp": {
+      "version": "0.30.7",
+      "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.30.7.tgz",
+      "integrity": "sha512-G+MY2YW33jgflKPTXXptVO28HvNOo9G3j0MybYAHeEmby+QuD2U98dT6ueht9cv/XDqZspSpIhoSW+BAKJ7Hig==",
+      "hasInstallScript": true,
+      "dependencies": {
+        "color": "^4.2.3",
+        "detect-libc": "^2.0.1",
+        "node-addon-api": "^5.0.0",
+        "prebuild-install": "^7.1.1",
+        "semver": "^7.3.7",
+        "simple-get": "^4.0.1",
+        "tar-fs": "^2.1.1",
+        "tunnel-agent": "^0.6.0"
+      },
+      "engines": {
+        "node": ">=12.13.0"
+      },
+      "funding": {
+        "url": "https://opencollective.com/libvips"
+      }
+    },
     "node_modules/shebang-command": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
@@ -10806,6 +11111,87 @@
       "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-3.0.7.tgz",
       "integrity": "sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ=="
     },
+    "node_modules/simple-concat": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/simple-concat/-/simple-concat-1.0.1.tgz",
+      "integrity": "sha512-cSFtAPtRhljv69IK0hTVZQ+OfE9nePi/rtJmw5UjHeVyVroEqJXP1sFztKUy1qU+xvz3u/sfYJLa947b7nAN2Q==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ]
+    },
+    "node_modules/simple-get": {
+      "version": "4.0.1",
+      "resolved": "https://registry.npmjs.org/simple-get/-/simple-get-4.0.1.tgz",
+      "integrity": "sha512-brv7p5WgH0jmQJr1ZDDfKDOSeWWg+OVypG99A/5vYGPqJ6pxiaHLy8nxtFjBA7oMa01ebA9gfh1uMCFqOuXxvA==",
+      "funding": [
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/feross"
+        },
+        {
+          "type": "patreon",
+          "url": "https://www.patreon.com/feross"
+        },
+        {
+          "type": "consulting",
+          "url": "https://feross.org/support"
+        }
+      ],
+      "dependencies": {
+        "decompress-response": "^6.0.0",
+        "once": "^1.3.1",
+        "simple-concat": "^1.0.0"
+      }
+    },
+    "node_modules/simple-get/node_modules/decompress-response": {
+      "version": "6.0.0",
+      "resolved": "https://registry.npmjs.org/decompress-response/-/decompress-response-6.0.0.tgz",
+      "integrity": "sha512-aW35yZM6Bb/4oJlZncMH2LCoZtJXTRxES17vE3hoRiowU2kWHaJKFkSBDnDR+cm9J+9QhXmREyIfv0pji9ejCQ==",
+      "dependencies": {
+        "mimic-response": "^3.1.0"
+      },
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/simple-get/node_modules/mimic-response": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/mimic-response/-/mimic-response-3.1.0.tgz",
+      "integrity": "sha512-z0yWI+4FDrrweS8Zmt4Ej5HdJmky15+L2e6Wgn3+iK5fWzb6T3fhNFq2+MeTRb064c6Wr4N/wv0DzQTjNzHNGQ==",
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/simple-swizzle": {
+      "version": "0.2.2",
+      "resolved": "https://registry.npmjs.org/simple-swizzle/-/simple-swizzle-0.2.2.tgz",
+      "integrity": "sha512-JA//kQgZtbuY83m+xT+tXJkmJncGMTFT+C+g2h2R9uxkYIrE2yy9sgmcLhCnw57/WSD+Eh3J97FPEDFnbXnDUg==",
+      "dependencies": {
+        "is-arrayish": "^0.3.1"
+      }
+    },
+    "node_modules/simple-swizzle/node_modules/is-arrayish": {
+      "version": "0.3.2",
+      "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.3.2.tgz",
+      "integrity": "sha512-eVRqCvVlZbuw3GrM63ovNSNAeA1K16kaR/LRY/92w0zxQ5/1YzwblUX652i4Xs9RwAGjW9d9y6X88t8OaAJfWQ=="
+    },
     "node_modules/sirv": {
       "version": "1.0.19",
       "resolved": "https://registry.npmjs.org/sirv/-/sirv-1.0.19.tgz",
@@ -10865,6 +11251,14 @@
         "websocket-driver": "^0.7.4"
       }
     },
+    "node_modules/sockjs/node_modules/uuid": {
+      "version": "8.3.2",
+      "resolved": "https://registry.npmjs.org/uuid/-/uuid-8.3.2.tgz",
+      "integrity": "sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==",
+      "bin": {
+        "uuid": "dist/bin/uuid"
+      }
+    },
     "node_modules/sort-css-media-queries": {
       "version": "2.1.0",
       "resolved": "https://registry.npmjs.org/sort-css-media-queries/-/sort-css-media-queries-2.1.0.tgz",
@@ -11217,6 +11611,32 @@
         "node": ">=6"
       }
     },
+    "node_modules/tar-fs": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/tar-fs/-/tar-fs-2.1.1.tgz",
+      "integrity": "sha512-V0r2Y9scmbDRLCNex/+hYzvp/zyYjvFbHPNgVTKfQvVrb6guiE/fxP+XblDNR011utopbkex2nM4dHNV6GDsng==",
+      "dependencies": {
+        "chownr": "^1.1.1",
+        "mkdirp-classic": "^0.5.2",
+        "pump": "^3.0.0",
+        "tar-stream": "^2.1.4"
+      }
+    },
+    "node_modules/tar-stream": {
+      "version": "2.2.0",
+      "resolved": "https://registry.npmjs.org/tar-stream/-/tar-stream-2.2.0.tgz",
+      "integrity": "sha512-ujeqbceABgwMZxEJnk2HDY2DlnUZ+9oEcb1KzTVfYHio0UE6dG71n60d8D2I4qNvleWrrXpmjpt7vZeF1LnMZQ==",
+      "dependencies": {
+        "bl": "^4.0.3",
+        "end-of-stream": "^1.4.1",
+        "fs-constants": "^1.0.0",
+        "inherits": "^2.0.3",
+        "readable-stream": "^3.1.1"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/terser": {
       "version": "5.19.2",
       "resolved": "https://registry.npmjs.org/terser/-/terser-5.19.2.tgz",
@@ -11413,6 +11833,17 @@
       "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.1.tgz",
       "integrity": "sha512-t0hLfiEKfMUoqhG+U1oid7Pva4bbDPHYfJNiB7BiIjRkj1pyC++4N3huJfqY6aRH6VTB0rvtzQwjM4K6qpfOig=="
     },
+    "node_modules/tunnel-agent": {
+      "version": "0.6.0",
+      "resolved": "https://registry.npmjs.org/tunnel-agent/-/tunnel-agent-0.6.0.tgz",
+      "integrity": "sha512-McnNiV1l8RYeY8tBgEpuodCC1mLUdbSN+CYBL7kJsJNInOP8UjDDEwdk6Mw60vdLLrr5NHKZhMAOSrR2NZuQ+w==",
+      "dependencies": {
+        "safe-buffer": "^5.0.1"
+      },
+      "engines": {
+        "node": "*"
+      }
+    },
     "node_modules/type-fest": {
       "version": "2.19.0",
       "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-2.19.0.tgz",
@@ -11991,9 +12422,9 @@
       }
     },
     "node_modules/uuid": {
-      "version": "8.3.2",
+      "version": "9.0.0",
-      "resolved": "https://registry.npmjs.org/uuid/-/uuid-8.3.2.tgz",
+      "resolved": "https://registry.npmjs.org/uuid/-/uuid-9.0.0.tgz",
-      "integrity": "sha512-+NYs2QeMWy+GWFOEm9xnn6HCDp0l7QBD7ml8zLUmJ+93Q5NF0NocErnwkTkXVFNiX3/fpC6afS8Dhb/gz7R7eg==",
+      "integrity": "sha512-MXcSTerfPa4uqyzStbRoTgt5XIe3x5+42+q1sDuy3R5MDk66URdLMOZe5aPX/SQd+kuYAh0FdP/pO28IkQyTeg==",
       "bin": {
         "uuid": "dist/bin/uuid"
       }

docs/my-website/package.json

@@ -15,12 +15,16 @@
   },
   "dependencies": {
     "@docusaurus/core": "2.4.1",
+    "@docusaurus/plugin-ideal-image": "^2.4.1",
     "@docusaurus/preset-classic": "2.4.1",
     "@mdx-js/react": "^1.6.22",
     "clsx": "^1.2.1",
+    "docusaurus-lunr-search": "^2.4.1",
     "prism-react-renderer": "^1.3.5",
     "react": "^17.0.2",
-    "react-dom": "^17.0.2"
+    "react-dom": "^17.0.2",
+    "sharp": "^0.32.5",
+    "uuid": "^9.0.0"
   },
   "devDependencies": {
     "@docusaurus/module-type-aliases": "2.4.1"

docs/my-website/sidebars.js

@@ -28,16 +28,13 @@ const sidebars = {
       label: "Embedding()",
       items: ["embedding/supported_embedding"],
     },
-    "debugging/local_debugging",
+    'completion/supported',
-    "completion/supported",
+    'debugging/local_debugging',
+    'debugging/hosted_debugging',
     {
-      type: "category",
+      type: 'category',
-      label: "Tutorials",
+      label: 'Tutorials',
-      items: [
+      items: ['tutorials/huggingface_tutorial', 'tutorials/TogetherAI_liteLLM', 'tutorials/fallbacks', 'tutorials/finetuned_chat_gpt'],
-        "tutorials/huggingface_tutorial",
-        "tutorials/TogetherAI_liteLLM",
-        "tutorials/debugging_tutorial",
-      ],
     },
     "token_usage",
     "stream",

litellm/__init__.py

@@ -1,9 +1,11 @@
 import threading
 from typing import Callable, List, Optional
+
 input_callback: List[str] = []
 success_callback: List[str] = []
 failure_callback: List[str] = []
 set_verbose = False
+email: Optional[str] = None  # for hosted dashboard. Learn more - https://docs.litellm.ai/docs/debugging/hosted_debugging
 telemetry = True
 max_tokens = 256  # OpenAI Defaults
 retry = True
@@ -17,10 +19,10 @@ openrouter_key: Optional[str] = None
 huggingface_key: Optional[str] = None
 vertex_project: Optional[str] = None
 vertex_location: Optional[str] = None
-hugging_api_token: Optional[str] = None
 togetherai_api_key: Optional[str] = None
 caching = False
-caching_with_models = False # if you want the caching key to be model + prompt
+caching_with_models = False  # if you want the caching key to be model + prompt
+debugger = False
 model_cost = {
     "gpt-3.5-turbo": {
         "max_tokens": 4000,
@@ -148,7 +150,15 @@ cohere_models = [
 anthropic_models = ["claude-2", "claude-instant-1", "claude-instant-1.2"]
 
 replicate_models = [
-    "replicate/"
+    "replicate/",
+    "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
+    "a16z-infra/llama-2-13b-chat:2a7f981751ec7fdf87b5b91ad4db53683a98082e9ff7bfd12c8cd5ea85980a52",
+    "joehoover/instructblip-vicuna13b:c4c54e3c8c97cd50c2d2fec9be3b6065563ccf7d43787fb99f84151b867178fe"
+    "replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5",
+    "a16z-infra/llama-2-7b-chat:7b0bfc9aff140d5b75bacbed23e91fd3c34b01a1e958d32132de6e0a19796e2c",
+    "replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b",
+    "daanelson/flan-t5-large:ce962b3f6792a57074a601d3979db5839697add2e4e02696b3ced4c022d4767f",
+    "replit/replit-code-v1-3b:b84f4c074b807211cd75e3e8b1589b6399052125b4c27106e43d47189e8415ad",
 ]  # placeholder, to make sure we accept any replicate model in our model_list
 
 openrouter_models = [
@@ -185,6 +195,14 @@ huggingface_models = [
 
 ai21_models = ["j2-ultra", "j2-mid", "j2-light"]
 
+together_ai_models = [
+    "togethercomputer/llama-2-70b-chat",
+    "togethercomputer/Llama-2-7B-32K-Instruct",
+    "togethercomputer/llama-2-7b",
+]
+
+baseten_models = ["qvv0xeq", "q841o8w", "31dxrj3"]  # FALCON 7B  # WizardLM  # Mosaic ML
+
 model_list = (
     open_ai_chat_completion_models
     + open_ai_text_completion_models
@@ -196,10 +214,13 @@ model_list = (
     + vertex_chat_models
     + vertex_text_models
     + ai21_models
+    + together_ai_models
+    + baseten_models
 )
 
 provider_list = [
     "openai",
+    "azure",
     "cohere",
     "anthropic",
     "replicate",
@@ -208,7 +229,22 @@ provider_list = [
     "openrouter",
     "vertex_ai",
     "ai21",
+    "baseten",
 ]
+
+models_by_provider = {
+    "openai": open_ai_chat_completion_models + open_ai_text_completion_models,
+    "cohere": cohere_models,
+    "anthropic": anthropic_models,
+    "replicate": replicate_models,
+    "huggingface": huggingface_models,
+    "together_ai": together_ai_models,
+    "baseten": baseten_models,
+    "openrouter": openrouter_models,
+    "vertex_ai": vertex_chat_models + vertex_text_models,
+    "ai21": ai21_models,
+}
+
 ####### EMBEDDING MODELS ###################
 open_ai_embedding_models = ["text-embedding-ada-002"]
 
@@ -223,7 +259,9 @@ from .utils import (
     cost_per_token,
     completion_cost,
     get_litellm_params,
-    Logging
+    Logging,
+    acreate,
+    get_model_list,
 )
 from .main import *  # type: ignore
 from .integrations import *

litellm/_version.py

@@ -0,0 +1,5 @@
+import importlib_metadata
+try:
+    version = importlib_metadata.version("litellm")
+except:
+    pass

litellm/integrations/litedebugger.py

@@ -1,10 +1,32 @@
-import requests, traceback, json
+import requests, traceback, json, os
+
+
 class LiteDebugger:
-    def __init__(self):
+    user_email = None
+    dashboard_url = None
+
+    def __init__(self, email=None):
         self.api_url = "https://api.litellm.ai/debugger"
+        self.validate_environment(email)
         pass
 
-    def input_log_event(self, model, messages, end_user, litellm_call_id, print_verbose):
+    def validate_environment(self, email):
+        try:
+            self.user_email = os.getenv("LITELLM_EMAIL") or email
+            self.dashboard_url = "https://admin.litellm.ai/" + self.user_email
+            print(f"Here's your free Dashboard 👉 {self.dashboard_url}")
+            if self.user_email == None:
+                raise Exception(
+                    "[Non-Blocking Error] LiteLLMDebugger: Missing LITELLM_EMAIL. Set it in your environment. Eg.: os.environ['LITELLM_EMAIL']= <your_email>"
+                )
+        except Exception as e:
+            raise ValueError(
+                "[Non-Blocking Error] LiteLLMDebugger: Missing LITELLM_EMAIL. Set it in your environment. Eg.: os.environ['LITELLM_EMAIL']= <your_email>"
+            )
+
+    def input_log_event(
+        self, model, messages, end_user, litellm_call_id, print_verbose
+    ):
         try:
             print_verbose(
                 f"LiteLLMDebugger: Logging - Enters input logging function for model {model}"
@@ -14,27 +36,37 @@ class LiteDebugger:
                 "messages": messages,
                 "end_user": end_user,
                 "status": "initiated",
-                "litellm_call_id": litellm_call_id
+                "litellm_call_id": litellm_call_id,
+                "user_email": self.user_email,
             }
-            response = requests.post(url=self.api_url, headers={"content-type": "application/json"}, data=json.dumps(litellm_data_obj))
+            response = requests.post(
+                url=self.api_url,
+                headers={"content-type": "application/json"},
+                data=json.dumps(litellm_data_obj),
+            )
             print_verbose(f"LiteDebugger: api response - {response.text}")
         except:
-            print_verbose(f"LiteDebugger: Logging Error - {traceback.format_exc()}")
+            print_verbose(
+                f"[Non-Blocking Error] LiteDebugger: Logging Error - {traceback.format_exc()}"
+            )
             pass
 
-    def log_event(self, model,
+    def log_event(
+        self,
+        model,
         messages,
         end_user,
         response_obj,
         start_time,
         end_time,
         litellm_call_id,
-        print_verbose,):
+        print_verbose,
+    ):
         try:
             print_verbose(
                 f"LiteLLMDebugger: Logging - Enters input logging function for model {model}"
             )
-            total_cost = 0 # [TODO] implement cost tracking
+            total_cost = 0  # [TODO] implement cost tracking
             response_time = (end_time - start_time).total_seconds()
             if "choices" in response_obj:
                 litellm_data_obj = {
@@ -45,12 +77,17 @@ class LiteDebugger:
                     "response": response_obj["choices"][0]["message"]["content"],
                     "end_user": end_user,
                     "litellm_call_id": litellm_call_id,
-                    "status": "success"
+                    "status": "success",
+                    "user_email": self.user_email,
                 }
                 print_verbose(
                     f"LiteDebugger: Logging - final data object: {litellm_data_obj}"
                 )
-                response = requests.post(url=self.api_url, headers={"content-type": "application/json"}, data=json.dumps(litellm_data_obj))
+                response = requests.post(
+                    url=self.api_url,
+                    headers={"content-type": "application/json"},
+                    data=json.dumps(litellm_data_obj),
+                )
             elif "error" in response_obj:
                 if "Unable to map your input to a model." in response_obj["error"]:
                     total_cost = 0
@@ -62,13 +99,20 @@ class LiteDebugger:
                     "error": response_obj["error"],
                     "end_user": end_user,
                     "litellm_call_id": litellm_call_id,
-                    "status": "failure"
+                    "status": "failure",
+                    "user_email": self.user_email,
                 }
                 print_verbose(
                     f"LiteDebugger: Logging - final data object: {litellm_data_obj}"
                 )
-                response = requests.post(url=self.api_url, headers={"content-type": "application/json"}, data=json.dumps(litellm_data_obj))
+                response = requests.post(
+                    url=self.api_url,
+                    headers={"content-type": "application/json"},
+                    data=json.dumps(litellm_data_obj),
+                )
                 print_verbose(f"LiteDebugger: api response - {response.text}")
         except:
-            print_verbose(f"LiteDebugger: Logging Error - {traceback.format_exc()}")
+            print_verbose(
+                f"[Non-Blocking Error] LiteDebugger: Logging Error - {traceback.format_exc()}"
+            )
             pass

litellm/integrations/supabase.py

@@ -144,7 +144,9 @@ class Supabase:
             )
         return prompt_tokens_cost_usd_dollar, completion_tokens_cost_usd_dollar
 
-    def input_log_event(self, model, messages, end_user, litellm_call_id, print_verbose):
+    def input_log_event(
+        self, model, messages, end_user, litellm_call_id, print_verbose
+    ):
         try:
             print_verbose(
                 f"Supabase Logging - Enters input logging function for model {model}"
@@ -154,13 +156,13 @@ class Supabase:
                 "messages": messages,
                 "end_user": end_user,
                 "status": "initiated",
-                "litellm_call_id": litellm_call_id
+                "litellm_call_id": litellm_call_id,
             }
             data, count = (
-                    self.supabase_client.table(self.supabase_table_name)
+                self.supabase_client.table(self.supabase_table_name)
-                    .insert(supabase_data_obj)
+                .insert(supabase_data_obj)
-                    .execute()
+                .execute()
-                )
+            )
             print(f"data: {data}")
         except:
             print_verbose(f"Supabase Logging Error - {traceback.format_exc()}")
@@ -200,7 +202,7 @@ class Supabase:
                     "response": response_obj["choices"][0]["message"]["content"],
                     "end_user": end_user,
                     "litellm_call_id": litellm_call_id,
-                    "status": "success"
+                    "status": "success",
                 }
                 print_verbose(
                     f"Supabase Logging - final data object: {supabase_data_obj}"
@@ -221,7 +223,7 @@ class Supabase:
                     "error": response_obj["error"],
                     "end_user": end_user,
                     "litellm_call_id": litellm_call_id,
-                    "status": "failure"
+                    "status": "failure",
                 }
                 print_verbose(
                     f"Supabase Logging - final data object: {supabase_data_obj}"

litellm/llms/anthropic.py

@@ -21,7 +21,9 @@ class AnthropicError(Exception):
 
 
 class AnthropicLLM:
-    def __init__(self, encoding, default_max_tokens_to_sample, logging_obj, api_key=None):
+    def __init__(
+        self, encoding, default_max_tokens_to_sample, logging_obj, api_key=None
+    ):
         self.encoding = encoding
         self.default_max_tokens_to_sample = default_max_tokens_to_sample
         self.completion_url = "https://api.anthropic.com/v1/complete"
@@ -84,7 +86,11 @@ class AnthropicLLM:
         }
 
         ## LOGGING
-        self.logging_obj.pre_call(input=prompt, api_key=self.api_key, additional_args={"complete_input_dict": data})
+        self.logging_obj.pre_call(
+            input=prompt,
+            api_key=self.api_key,
+            additional_args={"complete_input_dict": data},
+        )
         ## COMPLETION CALL
         response = requests.post(
             self.completion_url, headers=self.headers, data=json.dumps(data)
@@ -93,7 +99,12 @@ class AnthropicLLM:
             return response.iter_lines()
         else:
             ## LOGGING
-            self.logging_obj.post_call(input=prompt, api_key=self.api_key, original_response=response.text, additional_args={"complete_input_dict": data})
+            self.logging_obj.post_call(
+                input=prompt,
+                api_key=self.api_key,
+                original_response=response.text,
+                additional_args={"complete_input_dict": data},
+            )
             print_verbose(f"raw model_response: {response.text}")
             ## RESPONSE OBJECT
             completion_response = response.json()

litellm/llms/huggingface_restapi.py

@@ -72,12 +72,13 @@ class HuggingfaceRestAPILLM:
         if "max_tokens" in optional_params:
             value = optional_params.pop("max_tokens")
             optional_params["max_new_tokens"] = value
-        data = {
+        data = {"inputs": prompt, "parameters": optional_params}
-            "inputs": prompt,
-            "parameters": optional_params
-        }
         ## LOGGING
-        self.logging_obj.pre_call(input=prompt, api_key=self.api_key, additional_args={"complete_input_dict": data})
+        self.logging_obj.pre_call(
+            input=prompt,
+            api_key=self.api_key,
+            additional_args={"complete_input_dict": data},
+        )
         ## COMPLETION CALL
         response = requests.post(
             completion_url, headers=self.headers, data=json.dumps(data)
@@ -86,7 +87,12 @@ class HuggingfaceRestAPILLM:
             return response.iter_lines()
         else:
             ## LOGGING
-            self.logging_obj.post_call(input=prompt, api_key=self.api_key, original_response=response.text, additional_args={"complete_input_dict": data})
+            self.logging_obj.post_call(
+                input=prompt,
+                api_key=self.api_key,
+                original_response=response.text,
+                additional_args={"complete_input_dict": data},
+            )
             ## RESPONSE OBJECT
             completion_response = response.json()
             print_verbose(f"response: {completion_response}")

litellm/main.py

@@ -10,13 +10,14 @@ from litellm import (  # type: ignore
     timeout,
     get_optional_params,
     get_litellm_params,
-    Logging
+    Logging,
 )
 from litellm.utils import (
     get_secret,
     install_and_import,
     CustomStreamWrapper,
     read_config_args,
+    completion_with_fallbacks,
 )
 from .llms.anthropic import AnthropicLLM
 from .llms.huggingface_restapi import HuggingfaceRestAPILLM
@@ -90,17 +91,24 @@ def completion(
     # used by text-bison only
     top_k=40,
     request_timeout=0,  # unused var for old version of OpenAI API
+    fallbacks=[],
 ) -> ModelResponse:
+    args = locals()
     try:
+        if fallbacks != []:
+            return completion_with_fallbacks(**args)
         model_response = ModelResponse()
         if azure:  # this flag is deprecated, remove once notebooks are also updated.
             custom_llm_provider = "azure"
-        elif model.split("/", 1)[0] in litellm.provider_list: # allow custom provider to be passed in via the model name "azure/chatgpt-test"
+        elif (
+            model.split("/", 1)[0] in litellm.provider_list
+        ):  # allow custom provider to be passed in via the model name "azure/chatgpt-test"
             custom_llm_provider = model.split("/", 1)[0]
             model = model.split("/", 1)[1]
-            if "replicate" == custom_llm_provider and "/" not in model: # handle the "replicate/llama2..." edge-case
+            if (
+                "replicate" == custom_llm_provider and "/" not in model
+            ):  # handle the "replicate/llama2..." edge-case
                 model = custom_llm_provider + "/" + model
-        args = locals()
         # check if user passed in any of the OpenAI optional params
         optional_params = get_optional_params(
             functions=functions,
@@ -130,9 +138,14 @@ def completion(
             verbose=verbose,
             custom_llm_provider=custom_llm_provider,
             custom_api_base=custom_api_base,
-            litellm_call_id=litellm_call_id
+            litellm_call_id=litellm_call_id,
+        )
+        logging = Logging(
+            model=model,
+            messages=messages,
+            optional_params=optional_params,
+            litellm_params=litellm_params,
         )
-        logging = Logging(model=model, messages=messages, optional_params=optional_params, litellm_params=litellm_params)
         if custom_llm_provider == "azure":
             # azure configs
             openai.api_type = "azure"
@@ -153,7 +166,15 @@ def completion(
             # set key
             openai.api_key = api_key
             ## LOGGING
-            logging.pre_call(input=messages, api_key=openai.api_key, additional_args={"headers": litellm.headers, "api_version": openai.api_version, "api_base": openai.api_base})
+            logging.pre_call(
+                input=messages,
+                api_key=openai.api_key,
+                additional_args={
+                    "headers": litellm.headers,
+                    "api_version": openai.api_version,
+                    "api_base": openai.api_base,
+                },
+            )
             ## COMPLETION CALL
             if litellm.headers:
                 response = openai.ChatCompletion.create(
@@ -164,13 +185,24 @@ def completion(
                 )
             else:
                 response = openai.ChatCompletion.create(
-                    model=model, messages=messages, **optional_params
+                    engine=model, messages=messages, **optional_params
                 )
+
             ## LOGGING
-            logging.post_call(input=messages, api_key=openai.api_key, original_response=response, additional_args={"headers": litellm.headers, "api_version": openai.api_version, "api_base": openai.api_base})
+            logging.post_call(
+                input=messages,
+                api_key=openai.api_key,
+                original_response=response,
+                additional_args={
+                    "headers": litellm.headers,
+                    "api_version": openai.api_version,
+                    "api_base": openai.api_base,
+                },
+            )
         elif (
             model in litellm.open_ai_chat_completion_models
             or custom_llm_provider == "custom_openai"
+            or "ft:gpt-3.5-turbo" in model  # finetuned gpt-3.5-turbo
         ):  # allow user to make an openai call with a custom base
             openai.api_type = "openai"
             # note: if a user sets a custom base - we should ensure this works
@@ -192,7 +224,11 @@ def completion(
             openai.api_key = api_key
 
             ## LOGGING
-            logging.pre_call(input=messages, api_key=api_key, additional_args={"headers": litellm.headers, "api_base": api_base})
+            logging.pre_call(
+                input=messages,
+                api_key=api_key,
+                additional_args={"headers": litellm.headers, "api_base": api_base},
+            )
             ## COMPLETION CALL
             if litellm.headers:
                 response = openai.ChatCompletion.create(
@@ -206,7 +242,12 @@ def completion(
                     model=model, messages=messages, **optional_params
                 )
             ## LOGGING
-            logging.post_call(input=messages, api_key=api_key, original_response=response, additional_args={"headers": litellm.headers})
+            logging.post_call(
+                input=messages,
+                api_key=api_key,
+                original_response=response,
+                additional_args={"headers": litellm.headers},
+            )
         elif model in litellm.open_ai_text_completion_models:
             openai.api_type = "openai"
             openai.api_base = (
@@ -227,7 +268,16 @@ def completion(
                 openai.organization = litellm.organization
             prompt = " ".join([message["content"] for message in messages])
             ## LOGGING
-            logging.pre_call(input=prompt, api_key=api_key, additional_args={"openai_organization": litellm.organization, "headers": litellm.headers, "api_base": openai.api_base, "api_type": openai.api_type})
+            logging.pre_call(
+                input=prompt,
+                api_key=api_key,
+                additional_args={
+                    "openai_organization": litellm.organization,
+                    "headers": litellm.headers,
+                    "api_base": openai.api_base,
+                    "api_type": openai.api_type,
+                },
+            )
             ## COMPLETION CALL
             if litellm.headers:
                 response = openai.Completion.create(
@@ -238,7 +288,17 @@ def completion(
             else:
                 response = openai.Completion.create(model=model, prompt=prompt)
             ## LOGGING
-            logging.post_call(input=prompt, api_key=api_key, original_response=response, additional_args={"openai_organization": litellm.organization, "headers": litellm.headers, "api_base": openai.api_base, "api_type": openai.api_type})
+            logging.post_call(
+                input=prompt,
+                api_key=api_key,
+                original_response=response,
+                additional_args={
+                    "openai_organization": litellm.organization,
+                    "headers": litellm.headers,
+                    "api_base": openai.api_base,
+                    "api_type": openai.api_type,
+                },
+            )
             ## RESPONSE OBJECT
             completion_response = response["choices"][0]["text"]
             model_response["choices"][0]["message"]["content"] = completion_response
@@ -269,7 +329,14 @@ def completion(
                 input["max_length"] = max_tokens  # for t5 models
                 input["max_new_tokens"] = max_tokens  # for llama2 models
             ## LOGGING
-            logging.pre_call(input=prompt, api_key=replicate_key, additional_args={"complete_input_dict": input, "max_tokens": max_tokens})
+            logging.pre_call(
+                input=prompt,
+                api_key=replicate_key,
+                additional_args={
+                    "complete_input_dict": input,
+                    "max_tokens": max_tokens,
+                },
+            )
             ## COMPLETION CALL
             output = replicate.run(model, input=input)
             if "stream" in optional_params and optional_params["stream"] == True:
@@ -282,7 +349,15 @@ def completion(
                 response += item
             completion_response = response
             ## LOGGING
-            logging.post_call(input=prompt, api_key=replicate_key, original_response=completion_response, additional_args={"complete_input_dict": input, "max_tokens": max_tokens})
+            logging.post_call(
+                input=prompt,
+                api_key=replicate_key,
+                original_response=completion_response,
+                additional_args={
+                    "complete_input_dict": input,
+                    "max_tokens": max_tokens,
+                },
+            )
             ## USAGE
             prompt_tokens = len(encoding.encode(prompt))
             completion_tokens = len(encoding.encode(completion_response))
@@ -304,7 +379,7 @@ def completion(
                 encoding=encoding,
                 default_max_tokens_to_sample=litellm.max_tokens,
                 api_key=anthropic_key,
-                logging_obj = logging # model call logging done inside the class as we make need to modify I/O to fit anthropic's requirements
+                logging_obj=logging,  # model call logging done inside the class as we make need to modify I/O to fit anthropic's requirements
             )
             model_response = anthropic_client.completion(
                 model=model,
@@ -368,7 +443,9 @@ def completion(
                     **optional_params,
                 )
             ## LOGGING
-            logging.post_call(input=messages, api_key=openai.api_key, original_response=response)
+            logging.post_call(
+                input=messages, api_key=openai.api_key, original_response=response
+            )
         elif model in litellm.cohere_models:
             # import cohere/if it fails then pip install cohere
             install_and_import("cohere")
@@ -391,7 +468,9 @@ def completion(
                 response = CustomStreamWrapper(response, model)
                 return response
             ## LOGGING
-            logging.post_call(input=prompt, api_key=cohere_key, original_response=response)
+            logging.post_call(
+                input=prompt, api_key=cohere_key, original_response=response
+            )
             ## USAGE
             completion_response = response[0].text
             prompt_tokens = len(encoding.encode(prompt))
@@ -474,7 +553,9 @@ def completion(
                 headers=headers,
             )
             ## LOGGING
-            logging.post_call(input=prompt, api_key=TOGETHER_AI_TOKEN, original_response=res.text)
+            logging.post_call(
+                input=prompt, api_key=TOGETHER_AI_TOKEN, original_response=res.text
+            )
             # make this safe for reading, if output does not exist raise an error
             json_response = res.json()
             if "output" not in json_response:
@@ -515,7 +596,9 @@ def completion(
             completion_response = chat.send_message(prompt, **optional_params)
 
             ## LOGGING
-            logging.post_call(input=prompt, api_key=None, original_response=completion_response)
+            logging.post_call(
+                input=prompt, api_key=None, original_response=completion_response
+            )
 
             ## RESPONSE OBJECT
             model_response["choices"][0]["message"]["content"] = completion_response
@@ -540,7 +623,9 @@ def completion(
             completion_response = vertex_model.predict(prompt, **optional_params)
 
             ## LOGGING
-            logging.post_call(input=prompt, api_key=None, original_response=completion_response)
+            logging.post_call(
+                input=prompt, api_key=None, original_response=completion_response
+            )
             ## RESPONSE OBJECT
             model_response["choices"][0]["message"]["content"] = completion_response
             model_response["created"] = time.time()
@@ -563,7 +648,11 @@ def completion(
             completion_response = ai21_response["completions"][0]["data"]["text"]
 
             ## LOGGING
-            logging.post_call(input=prompt, api_key=ai21.api_key, original_response=completion_response)
+            logging.post_call(
+                input=prompt,
+                api_key=ai21.api_key,
+                original_response=completion_response,
+            )
 
             ## RESPONSE OBJECT
             model_response["choices"][0]["message"]["content"] = completion_response
@@ -577,7 +666,9 @@ def completion(
             prompt = " ".join([message["content"] for message in messages])
 
             ## LOGGING
-            logging.pre_call(input=prompt, api_key=None, additional_args={"endpoint": endpoint})
+            logging.pre_call(
+                input=prompt, api_key=None, additional_args={"endpoint": endpoint}
+            )
 
             generator = get_ollama_response_stream(endpoint, model, prompt)
             # assume all responses are streamed
@@ -604,7 +695,11 @@ def completion(
                     completion_response = completion_response["generated_text"]
 
             ## LOGGING
-            logging.post_call(input=prompt, api_key=base_ten_key, original_response=completion_response)
+            logging.post_call(
+                input=prompt,
+                api_key=base_ten_key,
+                original_response=completion_response,
+            )
 
             ## RESPONSE OBJECT
             model_response["choices"][0]["message"]["content"] = completion_response
@@ -621,13 +716,22 @@ def completion(
             prompt = " ".join([message["content"] for message in messages])
 
             ## LOGGING
-            logging.pre_call(input=prompt, api_key=None, additional_args={"url": url, "max_new_tokens": 100})
+            logging.pre_call(
+                input=prompt,
+                api_key=None,
+                additional_args={"url": url, "max_new_tokens": 100},
+            )
 
             response = requests.post(
                 url, data={"inputs": prompt, "max_new_tokens": 100, "model": model}
             )
             ## LOGGING
-            logging.post_call(input=prompt, api_key=None, original_response=response.text, additional_args={"url": url, "max_new_tokens": 100})
+            logging.post_call(
+                input=prompt,
+                api_key=None,
+                original_response=response.text,
+                additional_args={"url": url, "max_new_tokens": 100},
+            )
 
             completion_response = response.json()["outputs"]
 
@@ -637,7 +741,6 @@ def completion(
             model_response["model"] = model
             response = model_response
         else:
-            args = locals()
             raise ValueError(
                 f"Unable to map your input to a model. Check your input - {args}"
             )
@@ -676,10 +779,22 @@ def batch_completion(*args, **kwargs):
 @timeout(  # type: ignore
     60
 )  ## set timeouts, in case calls hang (e.g. Azure) - default is 60s, override with `force_timeout`
-def embedding(model, input=[], azure=False, force_timeout=60, litellm_call_id=None, logger_fn=None):
+def embedding(
+    model, input=[], azure=False, force_timeout=60, litellm_call_id=None, logger_fn=None
+):
     try:
         response = None
-        logging = Logging(model=model, messages=input, optional_params={}, litellm_params={"azure": azure, "force_timeout": force_timeout, "logger_fn": logger_fn, "litellm_call_id": litellm_call_id})
+        logging = Logging(
+            model=model,
+            messages=input,
+            optional_params={},
+            litellm_params={
+                "azure": azure,
+                "force_timeout": force_timeout,
+                "logger_fn": logger_fn,
+                "litellm_call_id": litellm_call_id,
+            },
+        )
         if azure == True:
             # azure configs
             openai.api_type = "azure"
@@ -687,7 +802,15 @@ def embedding(model, input=[], azure=False, force_timeout=60, litellm_call_id=No
             openai.api_version = get_secret("AZURE_API_VERSION")
             openai.api_key = get_secret("AZURE_API_KEY")
             ## LOGGING
-            logging.pre_call(input=input, api_key=openai.api_key, additional_args={"api_type": openai.api_type, "api_base": openai.api_base, "api_version": openai.api_version})
+            logging.pre_call(
+                input=input,
+                api_key=openai.api_key,
+                additional_args={
+                    "api_type": openai.api_type,
+                    "api_base": openai.api_base,
+                    "api_version": openai.api_version,
+                },
+            )
             ## EMBEDDING CALL
             response = openai.Embedding.create(input=input, engine=model)
             print_verbose(f"response_value: {str(response)[:50]}")
@@ -697,7 +820,15 @@ def embedding(model, input=[], azure=False, force_timeout=60, litellm_call_id=No
             openai.api_version = None
             openai.api_key = get_secret("OPENAI_API_KEY")
             ## LOGGING
-            logging.pre_call(input=input, api_key=openai.api_key, additional_args={"api_type": openai.api_type, "api_base": openai.api_base, "api_version": openai.api_version})
+            logging.pre_call(
+                input=input,
+                api_key=openai.api_key,
+                additional_args={
+                    "api_type": openai.api_type,
+                    "api_base": openai.api_base,
+                    "api_version": openai.api_version,
+                },
+            )
             ## EMBEDDING CALL
             response = openai.Embedding.create(input=input, model=model)
             print_verbose(f"response_value: {str(response)[:50]}")
@@ -710,7 +841,11 @@ def embedding(model, input=[], azure=False, force_timeout=60, litellm_call_id=No
         ## LOGGING
         logging.post_call(input=input, api_key=openai.api_key, original_response=e)
         ## Map to OpenAI Exception
-        raise exception_type(model=model, original_exception=e, custom_llm_provider="azure" if azure==True else None)
+        raise exception_type(
+            model=model,
+            original_exception=e,
+            custom_llm_provider="azure" if azure == True else None,
+        )
 
 
 ####### HELPER FUNCTIONS ################

litellm/tests/test_async_fn.py

@@ -9,7 +9,7 @@ import asyncio
 sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
-from litellm import acompletion
+from litellm import acompletion, acreate
 
 
 async def test_get_response():
@@ -24,3 +24,16 @@ async def test_get_response():
 
 response = asyncio.run(test_get_response())
 print(response)
+
+# async def test_get_response():
+#     user_message = "Hello, how are you?"
+#     messages = [{"content": user_message, "role": "user"}]
+#     try:
+#         response = await acreate(model="gpt-3.5-turbo", messages=messages)
+#     except Exception as e:
+#         pytest.fail(f"error occurred: {e}")
+#     return response
+
+
+# response = asyncio.run(test_get_response())
+# print(response)

litellm/tests/test_caching.py

@@ -34,7 +34,6 @@ def test_caching():
         pytest.fail(f"Error occurred: {e}")
 
 
-
 def test_caching_with_models():
     litellm.caching_with_models = True
     response2 = completion(model="gpt-3.5-turbo", messages=messages)
@@ -47,6 +46,3 @@ def test_caching_with_models():
         print(f"response2: {response2}")
         print(f"response3: {response3}")
         pytest.fail(f"Error occurred: {e}")
-
-
-

litellm/tests/test_completion.py

@@ -12,6 +12,8 @@ import pytest
 import litellm
 from litellm import embedding, completion
 
+litellm.debugger = True
+
 # from infisical import InfisicalClient
 
 # litellm.set_verbose = True
@@ -28,14 +30,18 @@ def logger_fn(user_model_dict):
 def test_completion_custom_provider_model_name():
     try:
         response = completion(
-            model="together_ai/togethercomputer/llama-2-70b-chat", messages=messages, logger_fn=logger_fn
+            model="together_ai/togethercomputer/llama-2-70b-chat",
+            messages=messages,
+            logger_fn=logger_fn,
         )
         # Add any assertions here to check the response
         print(response)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
-test_completion_custom_provider_model_name()
+
+# test_completion_custom_provider_model_name()
+
 
 def test_completion_claude():
     try:
@@ -89,7 +95,10 @@ def test_completion_claude_stream():
 def test_completion_cohere():
     try:
         response = completion(
-            model="command-nightly", messages=messages, max_tokens=100, logit_bias={40: 10}
+            model="command-nightly",
+            messages=messages,
+            max_tokens=100,
+            logit_bias={40: 10},
         )
         # Add any assertions here to check the response
         print(response)
@@ -103,6 +112,7 @@ def test_completion_cohere():
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
+
 def test_completion_cohere_stream():
     try:
         messages = [
@@ -254,8 +264,7 @@ def test_completion_openai_with_functions():
 def test_completion_azure():
     try:
         response = completion(
-            model="gpt-3.5-turbo",
+            model="chatgpt-test",
-            deployment_id="chatgpt-test",
             messages=messages,
             custom_llm_provider="azure",
         )
@@ -340,6 +349,18 @@ def test_petals():
         pytest.fail(f"Error occurred: {e}")
 
 
+def test_completion_with_fallbacks():
+    fallbacks = ["gpt-3.5-turb", "gpt-3.5-turbo", "command-nightly"]
+    try:
+        response = completion(
+            model="bad-model", messages=messages, force_timeout=120, fallbacks=fallbacks
+        )
+        # Add any assertions here to check the response
+        print(response)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 # def test_baseten_falcon_7bcompletion():
 #     model_name = "qvv0xeq"
 #     try:

litellm/tests/test_get_model_list.py

@@ -0,0 +1,11 @@
+import os, sys, traceback
+
+sys.path.insert(
+    0, os.path.abspath("../..")
+)  # Adds the parent directory to the system path
+import litellm
+from litellm import get_model_list
+
+print(get_model_list())
+print(get_model_list())
+# print(litellm.model_list)

litellm/tests/test_litedebugger_integration.py

@@ -9,18 +9,16 @@
 # import litellm
 # from litellm import embedding, completion
 
-# litellm.input_callback = ["lite_debugger"]
-# litellm.success_callback = ["lite_debugger"]
-# litellm.failure_callback = ["lite_debugger"]
-
 # litellm.set_verbose = True
 
+# litellm.email = "krrish@berri.ai"
+
 # user_message = "Hello, how are you?"
 # messages = [{ "content": user_message,"role": "user"}]
 
 
 # #openai call
 # response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
-
+# print(f"response: {response}")
 # #bad request call
-# response = completion(model="chatgpt-test", messages=[{"role": "user", "content": "Hi 👋 - i'm a bad request"}])
+# # response = completion(model="chatgpt-test", messages=[{"role": "user", "content": "Hi 👋 - i'm a bad request"}])

litellm/tests/test_streaming.py

@@ -22,6 +22,32 @@ def logger_fn(model_call_object: dict):
 user_message = "Hello, how are you?"
 messages = [{"content": user_message, "role": "user"}]
 
+# test on openai completion call
+try:
+    response = completion(
+        model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
+    )
+    for chunk in response:
+        print(chunk["choices"][0]["delta"])
+    score += 1
+except:
+    print(f"error occurred: {traceback.format_exc()}")
+    pass
+
+
+# test on azure completion call
+try:
+    response = completion(
+        model="azure/chatgpt-test", messages=messages, stream=True, logger_fn=logger_fn
+    )
+    for chunk in response:
+        print(chunk["choices"][0]["delta"])
+    score += 1
+except:
+    print(f"error occurred: {traceback.format_exc()}")
+    pass
+
+
 # test on anthropic completion call
 try:
     response = completion(
@@ -35,19 +61,19 @@ except:
     pass
 
 
-# test on anthropic completion call
+# # test on huggingface completion call
-try:
+# try:
-    response = completion(
+#     response = completion(
-        model="meta-llama/Llama-2-7b-chat-hf",
+#         model="meta-llama/Llama-2-7b-chat-hf",
-        messages=messages,
+#         messages=messages,
-        custom_llm_provider="huggingface",
+#         custom_llm_provider="huggingface",
-        custom_api_base="https://s7c7gytn18vnu4tw.us-east-1.aws.endpoints.huggingface.cloud",
+#         custom_api_base="https://s7c7gytn18vnu4tw.us-east-1.aws.endpoints.huggingface.cloud",
-        stream=True,
+#         stream=True,
-        logger_fn=logger_fn,
+#         logger_fn=logger_fn,
-    )
+#     )
-    for chunk in response:
+#     for chunk in response:
-        print(chunk["choices"][0]["delta"])
+#         print(chunk["choices"][0]["delta"])
-    score += 1
+#     score += 1
-except:
+# except:
-    print(f"error occurred: {traceback.format_exc()}")
+#     print(f"error occurred: {traceback.format_exc()}")
-    pass
+#     pass

litellm/tests/test_supabase_integration.py

@@ -24,5 +24,6 @@
 # #openai call
 # response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
 
+# fix
 # #bad request call
 # response = completion(model="chatgpt-test", messages=[{"role": "user", "content": "Hi 👋 - i'm a bad request"}])

litellm/utils.py

@@ -1,7 +1,20 @@
-import aiohttp
+import sys
-import subprocess
+import dotenv, json, traceback, threading
-import importlib
+import subprocess, os
-from typing import List, Dict, Union, Optional
+import litellm, openai
+import random, uuid, requests
+import datetime, time
+import tiktoken
+
+encoding = tiktoken.get_encoding("cl100k_base")
+import importlib.metadata
+from .integrations.helicone import HeliconeLogger
+from .integrations.aispend import AISpendLogger
+from .integrations.berrispend import BerriSpendLogger
+from .integrations.supabase import Supabase
+from .integrations.litedebugger import LiteDebugger
+from openai.error import OpenAIError as OriginalError
+from openai.openai_object import OpenAIObject
 from .exceptions import (
     AuthenticationError,
     InvalidRequestError,
@@ -9,34 +22,10 @@ from .exceptions import (
     ServiceUnavailableError,
     OpenAIError,
 )
-from openai.openai_object import OpenAIObject
+from typing import List, Dict, Union, Optional
-from openai.error import OpenAIError as OriginalError
-from .integrations.llmonitor import LLMonitorLogger
-from .integrations.litedebugger import LiteDebugger
-from .integrations.supabase import Supabase
-from .integrations.berrispend import BerriSpendLogger
-from .integrations.aispend import AISpendLogger
-from .integrations.helicone import HeliconeLogger
-import pkg_resources
-import sys
-import dotenv
-import json
-import traceback
-import threading
-import subprocess
-import os
-import litellm
-import openai
-import random
-import uuid
-import requests
-import datetime
-import time
-import tiktoken
 
-encoding = tiktoken.get_encoding("cl100k_base")
 
-####### ENVIRONMENT VARIABLES ###################
+####### ENVIRONMENT VARIABLES ####################
 dotenv.load_dotenv()  # Loading env variables using dotenv
 sentry_sdk_instance = None
 capture_exception = None
@@ -49,12 +38,11 @@ aispendLogger = None
 berrispendLogger = None
 supabaseClient = None
 liteDebuggerClient = None
-llmonitorLogger = None
 callback_list: Optional[List[str]] = []
 user_logger_fn = None
 additional_details: Optional[Dict[str, str]] = {}
 local_cache: Optional[Dict[str, str]] = {}
-
+last_fetched_at = None
 ######## Model Response #########################
 # All liteLLM Model responses will be in this format, Follows the OpenAI Format
 # https://docs.litellm.ai/docs/completion/output
@@ -174,7 +162,7 @@ class Logging:
 
     def pre_call(self, input, api_key, additional_args={}):
         try:
-            print(f"logging pre call for model: {self.model}")
+            print_verbose(f"logging pre call for model: {self.model}")
             self.model_call_details["input"] = input
             self.model_call_details["api_key"] = api_key
             self.model_call_details["additional_args"] = additional_args
@@ -214,7 +202,7 @@ class Logging:
                         print_verbose("reaches litedebugger for logging!")
                         model = self.model
                         messages = self.messages
-                        print(f"liteDebuggerClient: {liteDebuggerClient}")
+                        print_verbose(f"liteDebuggerClient: {liteDebuggerClient}")
                         liteDebuggerClient.input_log_event(
                             model=model,
                             messages=messages,
@@ -271,7 +259,6 @@ class Logging:
 
     # Add more methods as needed
 
-
 def exception_logging(
     additional_args={},
     logger_fn=None,
@@ -305,20 +292,34 @@ def exception_logging(
 ####### CLIENT ###################
 # make it easy to log if completion/embedding runs succeeded or failed + see what happened | Non-Blocking
 def client(original_function):
+    global liteDebuggerClient, get_all_keys
 
-    def function_setup(
+      def function_setup(
         *args, **kwargs
     ):  # just run once to check if user wants to send their data anywhere - PostHog/Sentry/Slack/etc.
         try:
             global callback_list, add_breadcrumb, user_logger_fn
-            if (len(litellm.input_callback) > 0
+            if litellm.email is not None or os.getenv("LITELLM_EMAIL", None) is not None:  # add to input, success and failure callbacks if user is using hosted product
-                    or len(litellm.success_callback) > 0
+                get_all_keys()
-                    or len(litellm.failure_callback)
+                if "lite_debugger" not in callback_list:
-                    > 0) and len(callback_list) == 0:
+                    litellm.input_callback.append("lite_debugger")
+                    litellm.success_callback.append("lite_debugger")
+                    litellm.failure_callback.append("lite_debugger")
+            if (
+                len(litellm.input_callback) > 0
+                or len(litellm.success_callback) > 0
+                or len(litellm.failure_callback) > 0
+            ) and len(callback_list) == 0:
                 callback_list = list(
-                    set(litellm.input_callback + litellm.success_callback +
+                    set(
-                        litellm.failure_callback))
+                        litellm.input_callback
-                set_callbacks(callback_list=callback_list, )
+                        + litellm.success_callback
+                        + litellm.failure_callback
+                    )
+                )
+                set_callbacks(
+                    callback_list=callback_list,
+                )
             if add_breadcrumb:
                 add_breadcrumb(
                     category="litellm.llm_call",
@@ -432,6 +433,11 @@ def client(original_function):
                       kwargs),
             )  # don't interrupt execution of main thread
             my_thread.start()
+            if hasattr(e, "message"):
+                if (
+                    liteDebuggerClient and liteDebuggerClient.dashboard_url != None
+                ):  # make it easy to get to the debugger logs if you've initialized it
+                    e.message += f"\n Check the log in your dashboard - {liteDebuggerClient.dashboard_url}"
             raise e
 
     return wrapper
@@ -515,7 +521,7 @@ def get_litellm_params(
         "verbose": verbose,
         "custom_llm_provider": custom_llm_provider,
         "custom_api_base": custom_api_base,
-        "litellm_call_id": litellm_call_id
+        "litellm_call_id": litellm_call_id,
     }
 
     return litellm_params
@@ -738,7 +744,7 @@ def set_callbacks(callback_list):
                 supabaseClient = Supabase()
             elif callback == "lite_debugger":
                 print(f"instantiating lite_debugger")
-                liteDebuggerClient = LiteDebugger()
+                liteDebuggerClient = LiteDebugger(email=litellm.email)
     except Exception as e:
         raise e
 
@@ -1036,7 +1042,7 @@ def handle_success(args, kwargs, result, start_time, end_time):
                     print_verbose("reaches lite_debugger for logging!")
                     model = args[0] if len(args) > 0 else kwargs["model"]
                     messages = args[1] if len(args) > 1 else kwargs["messages"]
-                    print(f"liteDebuggerClient: {liteDebuggerClient}")
+                    print_verbose(f"liteDebuggerClient: {liteDebuggerClient}")
                     liteDebuggerClient.log_event(
                         model=model,
                         messages=messages,
@@ -1066,6 +1072,9 @@ def handle_success(args, kwargs, result, start_time, end_time):
         )
         pass
 
+def acreate(*args, **kwargs):  ## Thin client to handle the acreate langchain call
+    return litellm.acompletion(*args, **kwargs)
+
 
 def prompt_token_calculator(model, messages):
     # use tiktoken or anthropic's tokenizer depending on the model
@@ -1082,6 +1091,21 @@ def prompt_token_calculator(model, messages):
     return num_tokens
 
 
+def valid_model(model):
+    try:
+        # for a given model name, check if the user has the right permissions to access the model
+        if (
+            model in litellm.open_ai_chat_completion_models
+            or model in litellm.open_ai_text_completion_models
+        ):
+            openai.Model.retrieve(model)
+        else:
+            messages = [{"role": "user", "content": "Hello World"}]
+            litellm.completion(model=model, messages=messages)
+    except:
+        raise InvalidRequestError(message="", model=model, llm_provider="")
+
+
 # integration helper function
 def modify_integration(integration_name, integration_params):
     global supabaseClient
@@ -1089,9 +1113,65 @@ def modify_integration(integration_name, integration_params):
         if "table_name" in integration_params:
             Supabase.supabase_table_name = integration_params["table_name"]
 
+####### [BETA] HOSTED PRODUCT ################ - https://docs.litellm.ai/docs/debugging/hosted_debugging
 
+def get_all_keys(llm_provider=None):
+    try:
+        global last_fetched_at
+        # if user is using hosted product -> instantiate their env with their hosted api keys - refresh every 5 minutes
+        user_email = os.getenv("LITELLM_EMAIL") or litellm.email
+        if user_email:
+            time_delta = 0
+            if last_fetched_at != None:
+                current_time = time.time()
+                time_delta = current_time - last_fetched_at
+            if time_delta > 300 or last_fetched_at == None or llm_provider: # if the llm provider is passed in , assume this happening due to an AuthError for that provider
+                # make the api call
+                last_fetched_at = time.time()
+                print(f"last_fetched_at: {last_fetched_at}")
+                response = requests.post(url="http://api.litellm.ai/get_all_keys", headers={"content-type": "application/json"}, data=json.dumps({"user_email": user_email}))
+                print_verbose(f"get model key response: {response.text}")
+                data = response.json()
+                # update model list
+                for key, value in data["model_keys"].items(): # follows the LITELLM API KEY format - <UPPERCASE_PROVIDER_NAME>_API_KEY - e.g. HUGGINGFACE_API_KEY
+                    os.environ[key] = value
+                return "it worked!"
+            return None
+        # return None by default
+        return None
+    except:
+        print_verbose(f"[Non-Blocking Error] get_all_keys error - {traceback.format_exc()}")
+        pass
+
+def get_model_list():
+    global last_fetched_at
+    try:
+        # if user is using hosted product -> get their updated model list - refresh every 5 minutes
+        user_email = os.getenv("LITELLM_EMAIL") or litellm.email
+        if user_email:
+            time_delta = 0
+            if last_fetched_at != None:
+                current_time = time.time()
+                time_delta = current_time - last_fetched_at
+            if time_delta > 300 or last_fetched_at == None:
+                # make the api call
+                last_fetched_at = time.time()
+                print(f"last_fetched_at: {last_fetched_at}")
+                response = requests.post(url="http://api.litellm.ai/get_model_list", headers={"content-type": "application/json"}, data=json.dumps({"user_email": user_email}))
+                print_verbose(f"get_model_list response: {response.text}")
+                data = response.json()
+                # update model list
+                model_list = data["model_list"]
+                return model_list
+            return None
+        return None # return None by default
+    except:
+        print_verbose(f"[Non-Blocking Error] get_all_keys error - {traceback.format_exc()}")
+
+
+####### EXCEPTION MAPPING ################
 def exception_type(model, original_exception, custom_llm_provider):
-    global user_logger_fn
+    global user_logger_fn, liteDebuggerClient
     exception_mapping_worked = False
     try:
         if isinstance(original_exception, OriginalError):
@@ -1232,12 +1312,16 @@ def exception_type(model, original_exception, custom_llm_provider):
             },
             exception=e,
         )
+        ## AUTH ERROR 
+        if isinstance(e, AuthenticationError) and (litellm.email or "LITELLM_EMAIL" in os.environ):
+            threading.Thread(target=get_all_keys, args=(e.llm_provider,)).start()
         if exception_mapping_worked:
             raise e
         else:  # don't let an error with mapping interrupt the user from receiving an error from the llm api calls
             raise original_exception
 
 
+####### CRASH REPORTING ################
 def safe_crash_reporting(model=None, exception=None, custom_llm_provider=None):
     data = {
         "model": model,
@@ -1273,7 +1357,7 @@ def litellm_telemetry(data):
         payload = {
             "uuid": uuid_value,
             "data": data,
-            "version": pkg_resources.get_distribution("litellm").version,
+            "version:": importlib.metadata.version("litellm"),
         }
         # Make the POST request to litellm logging api
         response = requests.post(
@@ -1443,7 +1527,7 @@ async def stream_to_string(generator):
     return response
 
 
-########## Together AI streaming #############################
+########## Together AI streaming ############################# [TODO] move together ai to it's own llm class
 async def together_ai_completion_streaming(json_data, headers):
     session = aiohttp.ClientSession()
     url = "https://api.together.xyz/inference"
@@ -1480,3 +1564,49 @@ async def together_ai_completion_streaming(json_data, headers):
                         pass
     finally:
         await session.close()
+
+
+def completion_with_fallbacks(**kwargs):
+    response = None
+    rate_limited_models = set()
+    model_expiration_times = {}
+    start_time = time.time()
+    fallbacks = [kwargs["model"]] + kwargs["fallbacks"]
+    del kwargs["fallbacks"]  # remove fallbacks so it's not recursive
+
+    while response == None and time.time() - start_time < 45:
+        for model in fallbacks:
+            # loop thru all models
+            try:
+                if (
+                    model in rate_limited_models
+                ):  # check if model is currently cooling down
+                    if (
+                        model_expiration_times.get(model)
+                        and time.time() >= model_expiration_times[model]
+                    ):
+                        rate_limited_models.remove(
+                            model
+                        )  # check if it's been 60s of cool down and remove model
+                    else:
+                        continue  # skip model
+
+                # delete model from kwargs if it exists
+                if kwargs.get("model"):
+                    del kwargs["model"]
+
+                print("making completion call", model)
+                response = litellm.completion(**kwargs, model=model)
+
+                if response != None:
+                    return response
+
+            except Exception as e:
+                print(f"got exception {e} for model {model}")
+                rate_limited_models.add(model)
+                model_expiration_times[model] = (
+                    time.time() + 60
+                )  # cool down this selected model
+                # print(f"rate_limited_models {rate_limited_models}")
+                pass
+    return response

poetry.lock

@@ -423,13 +423,13 @@ files = [
 
 [[package]]
 name = "openai"
-version = "0.27.8"
+version = "0.27.9"
 description = "Python client library for the OpenAI API"
 optional = false
 python-versions = ">=3.7.1"
 files = [
-    {file = "openai-0.27.8-py3-none-any.whl", hash = "sha256:e0a7c2f7da26bdbe5354b03c6d4b82a2f34bd4458c7a17ae1a7092c3e397e03c"},
+    {file = "openai-0.27.9-py3-none-any.whl", hash = "sha256:6a3cf8e276d1a6262b50562fbc0cba7967cfebb78ed827d375986b48fdad6475"},
-    {file = "openai-0.27.8.tar.gz", hash = "sha256:2483095c7db1eee274cebac79e315a986c4e55207bb4fa7b82d185b3a2ed9536"},
+    {file = "openai-0.27.9.tar.gz", hash = "sha256:b687761c82f5ebb6f61efc791b2083d2d068277b94802d4d1369efe39851813d"},
 ]
 
 [package.dependencies]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.437"
+version = "0.1.457"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"
@@ -11,6 +11,7 @@ python = "^3.8"
 openai = "^0.27.8"
 python-dotenv = "^1.0.0"
 tiktoken = "^0.4.0"
+importlib-metadata = "^6.8.0"
 
 [build-system]
 requires = ["poetry-core"]