phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 02:34:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add new model provider Novita AI (#7582)

Browse source 
* feat: add new model provider Novita AI

* feat: use deepseek r1 model for examples in Novita AI docs

* fix: fix tests

* fix: fix tests for novita

* fix: fix novita transformation
This commit is contained in:
Jason 2025-03-26 00:03:46 +08:00 • committed by GitHub
parent b33c56cf10
commit 7a92a03565
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 581 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.env.example
View file

@ -20,6 +20,8 @@ REPLICATE_API_TOKEN = ""
ANTHROPIC_API_KEY = ""
# Infisical
INFISICAL_TOKEN = ""
# Novita AI
NOVITA_API_KEY = ""
# Development Configs
LITELLM_MASTER_KEY = "sk-1234"

1
README.md
View file

@ -335,6 +335,7 @@ curl 'http://0.0.0.0:4000/key/generate' \
| [xinference [Xorbits Inference]](https://docs.litellm.ai/docs/providers/xinference) | | | | | ✅ | |
| [FriendliAI](https://docs.litellm.ai/docs/providers/friendliai) | ✅ | ✅ | ✅ | ✅ | | |
| [Galadriel](https://docs.litellm.ai/docs/providers/galadriel) | ✅ | ✅ | ✅ | ✅ | | |
| [Novita AI](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link) | ✅ | ✅ | ✅ | ✅ | | |
[**Read the Docs**](https://docs.litellm.ai/docs/)

97
cookbook/LiteLLM_NovitaAI_Cookbook.ipynb vendored Normal file
View file

@ -0,0 +1,97 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "iFEmsVJI_2BR"
},
"source": [
"# LiteLLM NovitaAI Cookbook"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cBlUhCEP_xj4"
},
"outputs": [],
"source": [
"!pip install litellm"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "p-MQqWOT_1a7"
},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ['NOVITA_API_KEY'] = \"\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Ze8JqMqWAARO"
},
"outputs": [],
"source": [
"from litellm import completion\n",
"response = completion(\n",
" model=\"novita/deepseek/deepseek-r1\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "-LnhELrnAM_J"
},
"outputs": [],
"source": [
"response = completion(\n",
" model=\"novita/deepseek/deepseek-r1\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dJBOUYdwCEn1"
},
"outputs": [],
"source": [
"response = completion(\n",
" model=\"mistralai/mistral-7b-instruct\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}

112
cookbook/LiteLLM_OpenRouter.ipynb vendored
View file

@ -1,27 +1,13 @@
{
"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 OpenRouter Cookbook"
],
"metadata": {
"id": "iFEmsVJI_2BR"
}
},
"source": [
"# LiteLLM OpenRouter Cookbook"
]
},
{
"cell_type": "code",
@ -36,27 +22,20 @@
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"id": "p-MQqWOT_1a7"
},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ['OPENROUTER_API_KEY'] = \"\""
],
"metadata": {
"id": "p-MQqWOT_1a7"
},
"execution_count": 14,
"outputs": []
]
},
{
"cell_type": "code",
"source": [
"from litellm import completion\n",
"response = completion(\n",
" model=\"openrouter/google/palm-2-chat-bison\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
],
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@ -64,10 +43,8 @@
"id": "Ze8JqMqWAARO",
"outputId": "64f3e836-69fa-4f8e-fb35-088a913bbe98"
},
"execution_count": 11,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<OpenAIObject id=gen-W8FTMSIEorCp3vG5iYIgNMR4IeBv at 0x7c3dcef1f060> JSON: {\n",
@ -85,20 +62,23 @@
"}"
]
},
"execution_count": 11,
"metadata": {},
"execution_count": 11
"output_type": "execute_result"
}
],
"source": [
"from litellm import completion\n",
"response = completion(\n",
" model=\"openrouter/google/palm-2-chat-bison\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
},
{
"cell_type": "code",
"source": [
"response = completion(\n",
" model=\"openrouter/anthropic/claude-2\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
],
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@ -106,10 +86,8 @@
"id": "-LnhELrnAM_J",
"outputId": "d51c7ab7-d761-4bd1-f849-1534d9df4cd0"
},
"execution_count": 12,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<OpenAIObject id=gen-IiuV7ZNimDufVeutBHrl8ajPuzEh at 0x7c3dcea67560> JSON: {\n",
@ -128,20 +106,22 @@
"}"
]
},
"execution_count": 12,
"metadata": {},
"execution_count": 12
"output_type": "execute_result"
}
],
"source": [
"response = completion(\n",
" model=\"openrouter/anthropic/claude-2\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
},
{
"cell_type": "code",
"source": [
"response = completion(\n",
" model=\"openrouter/meta-llama/llama-2-70b-chat\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
],
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
@ -149,10 +129,8 @@
"id": "dJBOUYdwCEn1",
"outputId": "ffa18679-ec15-4dad-fe2b-68665cdf36b0"
},
"execution_count": 13,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<OpenAIObject id=gen-PyMd3yyJ0aQsCgIY9R8XGZoAtPbl at 0x7c3dceefcae0> JSON: {\n",
@ -170,10 +148,32 @@
"}"
]
},
"execution_count": 13,
"metadata": {},
"execution_count": 13
"output_type": "execute_result"
}
],
"source": [
"response = completion(\n",
" model=\"openrouter/meta-llama/llama-2-70b-chat\",\n",
" messages=[{\"role\": \"user\", \"content\": \"write code for saying hi\"}]\n",
")\n",
"response"
]
}
]
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
}

1
docs/my-website/docs/completion/input.md
View file

@ -62,6 +62,7 @@ Use `litellm.get_supported_openai_params()` for an updated list of params for ea
|Databricks| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | | | | | | | | | |
|ClarifAI| ✅ | ✅ | ✅ | |✅ | ✅ | | | | | | | | | | |
|Github| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | | | | ✅ |✅ (model dependent)|✅ (model dependent)| | |
|Novita AI| ✅ | ✅ | | ✅ | ✅ | ✅ | | ✅ | ✅ | ✅ | ✅ | | | ✅ | | | | | | | |
:::note
By default, LiteLLM raises an exception if the openai param being passed in isn't supported.

33
docs/my-website/docs/index.md
View file

@ -208,6 +208,22 @@ response = completion(
)
```
</TabItem>
<TabItem value="novita" label="Novita AI">
```python
from litellm import completion
import os
## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
os.environ["NOVITA_API_KEY"] = "novita-api-key"
response = completion(
model="novita/deepseek/deepseek-r1",
messages=[{ "content": "Hello, how are you?","role": "user"}]
)
```
</TabItem>
</Tabs>
@ -411,6 +427,23 @@ response = completion(
)
```
</TabItem>
<TabItem value="novita" label="Novita AI">
```python
from litellm import completion
import os
## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
os.environ["NOVITA_API_KEY"] = "novita_api_key"
response = completion(
model="novita/deepseek/deepseek-r1",
messages = [{ "content": "Hello, how are you?","role": "user"}],
stream=True,
)
```
</TabItem>
</Tabs>

39
docs/my-website/docs/providers/novita.md Normal file
View file

@ -0,0 +1,39 @@
# Novita AI
LiteLLM supports all models from [Novita AI](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
## Usage
```python
import os
from litellm import completion
os.environ["NOVITA_API_KEY"] = ""
response = completion(
model="meta-llama/llama-3.3-70b-instruct",
messages=messages,
)
```
## Novita AI Completion Models
🚨 LiteLLM supports ALL Novita AI models, send `model=novita/<your-novita-model>` to send it to Novita AI. See all Novita AI models [here](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
| Model Name | Function Call |
|---------------------------|-----------------------------------------------------|
| novita/deepseek/deepseek-r1 | `completion('novita/deepseek/deepseek-r1', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/deepseek/deepseek_v3 | `completion('novita/deepseek/deepseek_v3', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.3-70b-instruct | `completion('novita/meta-llama/llama-3.3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-8b-instruct | `completion('novita/meta-llama/llama-3.1-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-8b-instruct-max | `completion('novita/meta-llama/llama-3.1-8b-instruct-max', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-70b-instruct | `completion('novita/meta-llama/llama-3.1-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3-8b-instruct | `completion('novita/meta-llama/llama-3-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3-70b-instruct | `completion('novita/meta-llama/llama-3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-1b-instruct | `completion('novita/meta-llama/llama-3.2-1b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-11b-vision-instruct | `completion('novita/meta-llama/llama-3.2-11b-vision-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-3b-instruct | `completion('novita/meta-llama/llama-3.2-3b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/gryphe/mythomax-l2-13b | `completion('novita/gryphe/mythomax-l2-13b', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/google/gemma-2-9b-it | `completion('novita/google/gemma-2-9b-it', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/mistralai/mistral-nemo | `completion('novita/mistralai/mistral-nemo', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/mistralai/mistral-7b-instruct | `completion('novita/mistralai/mistral-7b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/qwen/qwen-2.5-72b-instruct | `completion('novita/qwen/qwen-2.5-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/qwen/qwen-2-vl-72b-instruct | `completion('novita/qwen/qwen-2-vl-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |

1
docs/my-website/sidebars.js
View file

@ -225,6 +225,7 @@ const sidebars = {
"providers/nlp_cloud",
"providers/replicate",
"providers/togetherai",
"providers/novita",
"providers/voyage",
"providers/jina_ai",
"providers/aleph_alpha",

2
docs/my-website/src/pages/completion/input.md
View file

@ -1,6 +1,6 @@
# Completion Function - completion()
The Input params are **exactly the same** as the
<a href="https://platform.openai.com/docs/api-reference/chat/create" target="_blank" rel="noopener noreferrer">OpenAI Create chat completion</a>, and let you call **Azure OpenAI, Anthropic, Cohere, Replicate, OpenRouter** models in the same format.
<a href="https://platform.openai.com/docs/api-reference/chat/create" target="_blank" rel="noopener noreferrer">OpenAI Create chat completion</a>, and let you call **Azure OpenAI, Anthropic, Cohere, Replicate, OpenRouter, Novita AI** models in the same format.
In addition, liteLLM allows you to pass in the following **Optional** liteLLM args:
`force_timeout`, `azure`, `logger_fn`, `verbose`

24
docs/my-website/src/pages/completion/supported.md
View file

@ -71,3 +71,27 @@ All the text models from [OpenRouter](https://openrouter.ai/docs) are supported
| google/palm-2-codechat-bison | `completion('google/palm-2-codechat-bison', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']` |
| meta-llama/llama-2-13b-chat | `completion('meta-llama/llama-2-13b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']` |
| meta-llama/llama-2-70b-chat | `completion('meta-llama/llama-2-70b-chat', messages)` | `os.environ['OR_SITE_URL']`,`os.environ['OR_APP_NAME']`,`os.environ['OR_API_KEY']` |
## Novita AI Completion Models
🚨 LiteLLM supports ALL Novita AI models, send `model=novita/<your-novita-model>` to send it to Novita AI. See all Novita AI models [here](https://novita.ai/models/llm?utm_source=github_litellm&utm_medium=github_readme&utm_campaign=github_link)
| Model Name | Function Call | Required OS Variables |
|------------------|--------------------------------------------|--------------------------------------|
| novita/deepseek/deepseek-r1 | `completion('novita/deepseek/deepseek-r1', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/deepseek/deepseek_v3 | `completion('novita/deepseek/deepseek_v3', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.3-70b-instruct | `completion('novita/meta-llama/llama-3.3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-8b-instruct | `completion('novita/meta-llama/llama-3.1-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-8b-instruct-max | `completion('novita/meta-llama/llama-3.1-8b-instruct-max', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.1-70b-instruct | `completion('novita/meta-llama/llama-3.1-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3-8b-instruct | `completion('novita/meta-llama/llama-3-8b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3-70b-instruct | `completion('novita/meta-llama/llama-3-70b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-1b-instruct | `completion('novita/meta-llama/llama-3.2-1b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-11b-vision-instruct | `completion('novita/meta-llama/llama-3.2-11b-vision-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/meta-llama/llama-3.2-3b-instruct | `completion('novita/meta-llama/llama-3.2-3b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/gryphe/mythomax-l2-13b | `completion('novita/gryphe/mythomax-l2-13b', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/google/gemma-2-9b-it | `completion('novita/google/gemma-2-9b-it', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/mistralai/mistral-nemo | `completion('novita/mistralai/mistral-nemo', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/mistralai/mistral-7b-instruct | `completion('novita/mistralai/mistral-7b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/qwen/qwen-2.5-72b-instruct | `completion('novita/qwen/qwen-2.5-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |
| novita/qwen/qwen-2-vl-72b-instruct | `completion('novita/qwen/qwen-2-vl-72b-instruct', messages)` | `os.environ['NOVITA_API_KEY']` |

32
docs/my-website/src/pages/index.md
View file

@ -194,6 +194,22 @@ response = completion(
)
```
</TabItem>
<TabItem value="novita" label="Novita AI">
```python
from litellm import completion
import os
## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
os.environ["NOVITA_API_KEY"] = "novita-api-key"
response = completion(
model="novita/deepseek/deepseek-r1",
messages=[{ "content": "Hello, how are you?","role": "user"}]
)
```
</TabItem>
</Tabs>
@ -347,7 +363,23 @@ response = completion(
```
</TabItem>
<TabItem value="novita" label="Novita AI">
```python
from litellm import completion
import os
## set ENV variables. Visit https://novita.ai/settings/key-management to get your API key
os.environ["NOVITA_API_KEY"] = "novita_api_key"
response = completion(
model="novita/deepseek/deepseek-r1",
messages = [{ "content": "Hello, how are you?","role": "user"}],
stream=True,
)
```
</TabItem>
</Tabs>
### Exception handling

8
litellm/__init__.py
View file

@ -182,6 +182,7 @@ cloudflare_api_key: Optional[str] = None
baseten_key: Optional[str] = None
aleph_alpha_key: Optional[str] = None
nlp_cloud_key: Optional[str] = None
novita_api_key: Optional[str] = None
snowflake_key: Optional[str] = None
common_cloud_provider_auth_params: dict = {
"params": ["project", "region_name", "token"],
@ -416,10 +417,10 @@ anyscale_models: List = []
cerebras_models: List = []
galadriel_models: List = []
sambanova_models: List = []
novita_models: List = []
assemblyai_models: List = []
snowflake_models: List = []
def is_bedrock_pricing_only_model(key: str) -> bool:
"""
Excludes keys with the pattern 'bedrock/<region>/<model>'. These are in the model_prices_and_context_window.json file for pricing purposes only.
@ -567,6 +568,8 @@ def add_known_models():
galadriel_models.append(key)
elif value.get("litellm_provider") == "sambanova_models":
sambanova_models.append(key)
elif value.get("litellm_provider") == "novita":
novita_models.append(key)
elif value.get("litellm_provider") == "assemblyai":
assemblyai_models.append(key)
elif value.get("litellm_provider") == "jina_ai":
@ -645,6 +648,7 @@ model_list = (
+ galadriel_models
+ sambanova_models
+ azure_text_models
+ novita_models
+ assemblyai_models
+ jina_ai_models
+ snowflake_models
@ -701,6 +705,7 @@ models_by_provider: dict = {
"cerebras": cerebras_models,
"galadriel": galadriel_models,
"sambanova": sambanova_models,
"novita": novita_models,
"assemblyai": assemblyai_models,
"jina_ai": jina_ai_models,
"snowflake": snowflake_models,
@ -835,6 +840,7 @@ from .llms.anthropic.experimental_pass_through.messages.transformation import (
from .llms.together_ai.chat import TogetherAIConfig
from .llms.together_ai.completion.transformation import TogetherAITextCompletionConfig
from .llms.cloudflare.chat.transformation import CloudflareChatConfig
from .llms.novita.chat.transformation import NovitaConfig
from .llms.deprecated_providers.palm import (
PalmConfig,
) # here to prevent breaking changes

2
litellm/constants.py
View file

@ -82,6 +82,7 @@ LITELLM_CHAT_PROVIDERS = [
"hosted_vllm",
"lm_studio",
"galadriel",
"novita",
]
@ -171,6 +172,7 @@ openai_compatible_providers: List = [
"hosted_vllm",
"lm_studio",
"galadriel",
"novita",
]
openai_text_completion_compatible_providers: List = (
[ # providers that support `/v1/completions`

7
litellm/litellm_core_utils/get_llm_provider_logic.py
View file

@ -569,6 +569,13 @@ def _get_openai_compatible_provider_info( # noqa: PLR0915
or "https://api.galadriel.com/v1"
) # type: ignore
dynamic_api_key = api_key or get_secret_str("GALADRIEL_API_KEY")
elif custom_llm_provider == "novita":
api_base = (
api_base
or get_secret("NOVITA_API_BASE")
or "https://api.novita.ai/v3/openai"
) # type: ignore
dynamic_api_key = api_key or get_secret_str("NOVITA_API_KEY")
elif custom_llm_provider == "snowflake":
api_base = (
api_base

2
litellm/litellm_core_utils/get_supported_openai_params.py
View file

@ -119,6 +119,8 @@ def get_supported_openai_params( # noqa: PLR0915
return litellm.GoogleAIStudioGeminiConfig().get_supported_openai_params(
model=model
)
elif custom_llm_provider == "novita":
return litellm.NovitaConfig().get_supported_openai_params(model=model)
elif custom_llm_provider == "vertex_ai" or custom_llm_provider == "vertex_ai_beta":
if request_type == "chat_completion":
if model.startswith("mistral"):

35
litellm/llms/novita/chat/transformation.py Normal file
View file

@ -0,0 +1,35 @@
"""
Support for OpenAI's `/v1/chat/completions` endpoint.
Calls done in OpenAI/openai.py as Novita AI is openai-compatible.
Docs: https://novita.ai/docs/guides/llm-api
"""
from typing import List, Optional
from ....types.llms.openai import AllMessageValues
from ...openai.chat.gpt_transformation import OpenAIGPTConfig
class NovitaConfig(OpenAIGPTConfig):
def validate_environment(
self,
headers: dict,
model: str,
messages: List[AllMessageValues],
optional_params: dict,
api_key: Optional[str] = None,
api_base: Optional[str] = None,
) -> dict:
if api_key is None:
raise ValueError(
"Missing Novita AI API Key - A call is being made to novita but no key is set either in the environment variables or via params"
)
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
"X-Novita-Source": "litellm",
}
return headers

1
litellm/main.py
View file

@ -3252,7 +3252,6 @@ async def aembedding(*args, **kwargs) -> EmbeddingResponse:
response = init_response
elif asyncio.iscoroutine(init_response):
response = await init_response # type: ignore
if (
response is not None
and isinstance(response, EmbeddingResponse)

1
litellm/types/utils.py
View file

@ -2015,6 +2015,7 @@ class LlmProviders(str, Enum):
GALADRIEL = "galadriel"
INFINITY = "infinity"
DEEPGRAM = "deepgram"
NOVITA = "novita"
AIOHTTP_OPENAI = "aiohttp_openai"
LANGFUSE = "langfuse"
HUMANLOOP = "humanloop"

15
litellm/utils.py
View file

@ -2317,6 +2317,9 @@ def register_model(model_cost: Union[str, dict]): # noqa: PLR0915
elif value.get("litellm_provider") == "bedrock":
if key not in litellm.bedrock_models:
litellm.bedrock_models.append(key)
elif value.get("litellm_provider") == "novita":
if key not in litellm.novita_models:
litellm.novita_models.append(key)
return model_cost
@ -5073,6 +5076,11 @@ def validate_environment( # noqa: PLR0915
else:
missing_keys.append("CLOUDFLARE_API_KEY")
missing_keys.append("CLOUDFLARE_API_BASE")
elif custom_llm_provider == "novita":
if "NOVITA_API_KEY" in os.environ:
keys_in_environment = True
else:
missing_keys.append("NOVITA_API_KEY")
else:
## openai - chatcompletion + text completion
if (
@ -5155,6 +5163,11 @@ def validate_environment( # noqa: PLR0915
keys_in_environment = True
else:
missing_keys.append("NLP_CLOUD_API_KEY")
elif model in litellm.novita_models:
if "NOVITA_API_KEY" in os.environ:
keys_in_environment = True
else:
missing_keys.append("NOVITA_API_KEY")
if api_key is not None:
new_missing_keys = []
@ -6281,6 +6294,8 @@ class ProviderConfigManager:
return litellm.TritonConfig()
elif litellm.LlmProviders.PETALS == provider:
return litellm.PetalsConfig()
elif litellm.LlmProviders.NOVITA == provider:
return litellm.NovitaConfig()
elif litellm.LlmProviders.BEDROCK == provider:
bedrock_route = BedrockModelInfo.get_bedrock_route(model)
bedrock_invoke_provider = litellm.BedrockLLM.get_bedrock_invoke_provider(

108
poetry.lock generated
View file

@ -123,7 +123,7 @@ multidict = ">=4.5,<7.0"
yarl = ">=1.12.0,<2.0"
[package.extras]
speedups = ["Brotli", "aiodns (>=3.2.0)", "brotlicffi"]
speedups = ["Brotli ; platform_python_implementation == \"CPython\"", "aiodns (>=3.2.0) ; sys_platform == \"linux\" or sys_platform == \"darwin\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
[[package]]
name = "aiosignal"
@ -175,7 +175,7 @@ typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
[package.extras]
doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "truststore (>=0.9.1)", "uvloop (>=0.21.0b1)"]
test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "truststore (>=0.9.1) ; python_version >= \"3.10\"", "uvloop (>=0.21.0b1) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\""]
trio = ["trio (>=0.26.1)"]
[[package]]
@ -203,7 +203,7 @@ mongodb = ["pymongo (>=3.0)"]
redis = ["redis (>=3.0)"]
rethinkdb = ["rethinkdb (>=2.4.0)"]
sqlalchemy = ["sqlalchemy (>=1.4)"]
test = ["APScheduler[etcd,mongodb,redis,rethinkdb,sqlalchemy,tornado,zookeeper]", "PySide6", "anyio (>=4.5.2)", "gevent", "pytest", "pytz", "twisted"]
test = ["APScheduler[etcd,mongodb,redis,rethinkdb,sqlalchemy,tornado,zookeeper]", "PySide6 ; platform_python_implementation == \"CPython\" and python_version < \"3.14\"", "anyio (>=4.5.2)", "gevent ; python_version < \"3.14\"", "pytest", "pytz", "twisted ; python_version < \"3.14\""]
tornado = ["tornado (>=4.3)"]
twisted = ["twisted"]
zookeeper = ["kazoo"]
@ -234,12 +234,12 @@ files = [
]
[package.extras]
benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier"]
tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\""]
[[package]]
name = "azure-core"
@ -386,7 +386,7 @@ typing-extensions = {version = ">=4.0.1", markers = "python_version < \"3.11\""}
[package.extras]
colorama = ["colorama (>=0.4.3)"]
d = ["aiohttp (>=3.7.4)", "aiohttp (>=3.7.4,!=3.9.0)"]
d = ["aiohttp (>=3.7.4) ; sys_platform != \"win32\" or implementation_name != \"pypy\"", "aiohttp (>=3.7.4,!=3.9.0) ; sys_platform == \"win32\" and implementation_name == \"pypy\""]
jupyter = ["ipython (>=7.8.0)", "tokenize-rt (>=3.2.0)"]
uvloop = ["uvloop (>=0.15.2)"]
@ -865,7 +865,7 @@ files = [
[package.extras]
docs = ["furo (>=2024.8.6)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4.1)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.6.1)", "diff-cover (>=9.2)", "pytest (>=8.3.3)", "pytest-asyncio (>=0.24)", "pytest-cov (>=5)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.26.4)"]
typing = ["typing-extensions (>=4.12.2)"]
typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
[[package]]
name = "flake8"
@ -1043,12 +1043,12 @@ files = [
google-auth = ">=2.14.1,<3.0.0"
googleapis-common-protos = ">=1.56.2,<2.0.0"
grpcio = [
{version = ">=1.33.2,<2.0dev", optional = true, markers = "extra == \"grpc\""},
{version = ">=1.49.1,<2.0dev", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
{version = ">=1.33.2,<2.0dev", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
]
grpcio-status = [
{version = ">=1.33.2,<2.0.dev0", optional = true, markers = "extra == \"grpc\""},
{version = ">=1.49.1,<2.0.dev0", optional = true, markers = "python_version >= \"3.11\" and extra == \"grpc\""},
{version = ">=1.33.2,<2.0.dev0", optional = true, markers = "python_version < \"3.11\" and extra == \"grpc\""},
]
proto-plus = [
{version = ">=1.22.3,<2.0.0", markers = "python_version < \"3.13\""},
@ -1059,7 +1059,7 @@ requests = ">=2.18.0,<3.0.0"
[package.extras]
async-rest = ["google-auth[aiohttp] (>=2.35.0,<3.0.dev0)"]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio (>=1.49.1,<2.0dev)", "grpcio-status (>=1.33.2,<2.0.dev0)", "grpcio-status (>=1.49.1,<2.0.dev0)"]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio (>=1.49.1,<2.0dev) ; python_version >= \"3.11\"", "grpcio-status (>=1.33.2,<2.0.dev0)", "grpcio-status (>=1.49.1,<2.0.dev0) ; python_version >= \"3.11\""]
grpcgcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"]
grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"]
@ -1352,6 +1352,66 @@ files = [
{file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
]
[[package]]
name = "h2"
version = "4.1.0"
description = "HTTP/2 State-Machine based protocol implementation"
optional = false
python-versions = ">=3.6.1"
groups = ["main"]
markers = "python_version < \"3.10\""
files = [
{file = "h2-4.1.0-py3-none-any.whl", hash = "sha256:03a46bcf682256c95b5fd9e9a99c1323584c3eec6440d379b9903d709476bc6d"},
{file = "h2-4.1.0.tar.gz", hash = "sha256:a83aca08fbe7aacb79fec788c9c0bac936343560ed9ec18b82a13a12c28d2abb"},
]
[package.dependencies]
hpack = ">=4.0,<5"
hyperframe = ">=6.0,<7"
[[package]]
name = "h2"
version = "4.2.0"
description = "Pure-Python HTTP/2 protocol implementation"
optional = false
python-versions = ">=3.9"
groups = ["main"]
markers = "python_version >= \"3.10\""
files = [
{file = "h2-4.2.0-py3-none-any.whl", hash = "sha256:479a53ad425bb29af087f3458a61d30780bc818e4ebcf01f0b536ba916462ed0"},
{file = "h2-4.2.0.tar.gz", hash = "sha256:c8a52129695e88b1a0578d8d2cc6842bbd79128ac685463b887ee278126ad01f"},
]
[package.dependencies]
hpack = ">=4.1,<5"
hyperframe = ">=6.1,<7"
[[package]]
name = "hpack"
version = "4.0.0"
description = "Pure-Python HPACK header compression"
optional = false
python-versions = ">=3.6.1"
groups = ["main"]
markers = "python_version < \"3.10\""
files = [
{file = "hpack-4.0.0-py3-none-any.whl", hash = "sha256:84a076fad3dc9a9f8063ccb8041ef100867b1878b25ef0ee63847a5d53818a6c"},
{file = "hpack-4.0.0.tar.gz", hash = "sha256:fc41de0c63e687ebffde81187a948221294896f6bdc0ae2312708df339430095"},
]
[[package]]
name = "hpack"
version = "4.1.0"
description = "Pure-Python HPACK header encoding"
optional = false
python-versions = ">=3.9"
groups = ["main"]
markers = "python_version >= \"3.10\""
files = [
{file = "hpack-4.1.0-py3-none-any.whl", hash = "sha256:157ac792668d995c657d93111f46b4535ed114f0c9c8d672271bbec7eae1b496"},
{file = "hpack-4.1.0.tar.gz", hash = "sha256:ec5eca154f7056aa06f196a557655c5b009b382873ac8d1e66e79e87535f1dca"},
]
[[package]]
name = "httpcore"
version = "1.0.7"
@ -1393,7 +1453,7 @@ httpcore = "==1.*"
idna = "*"
[package.extras]
brotli = ["brotli", "brotlicffi"]
brotli = ["brotli ; platform_python_implementation == \"CPython\"", "brotlicffi ; platform_python_implementation != \"CPython\""]
cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
http2 = ["h2 (>=3,<5)"]
socks = ["socksio (==1.*)"]
@ -1481,12 +1541,12 @@ files = [
zipp = ">=3.20"
[package.extras]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
cover = ["pytest-cov"]
doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
enabler = ["pytest-enabler (>=2.2)"]
perf = ["ipython"]
test = ["flufl.flake8", "importlib-resources (>=1.3)", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-perf (>=0.9.2)"]
test = ["flufl.flake8", "importlib-resources (>=1.3) ; python_version < \"3.9\"", "jaraco.test (>=5.4)", "packaging", "pyfakefs", "pytest (>=6,!=8.1.*)", "pytest-perf (>=0.9.2)"]
type = ["pytest-mypy"]
[[package]]
@ -1506,7 +1566,7 @@ files = [
zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
[package.extras]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
cover = ["pytest-cov"]
doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
enabler = ["pytest-enabler (>=2.2)"]
@ -1835,7 +1895,7 @@ PyJWT = {version = ">=1.0.0,<3", extras = ["crypto"]}
requests = ">=2.0.0,<3"
[package.extras]
broker = ["pymsalruntime (>=0.14,<0.18)", "pymsalruntime (>=0.17,<0.18)"]
broker = ["pymsalruntime (>=0.14,<0.18) ; python_version >= \"3.6\" and platform_system == \"Windows\"", "pymsalruntime (>=0.17,<0.18) ; python_version >= \"3.8\" and platform_system == \"Darwin\""]
[[package]]
name = "msal-extensions"
@ -2614,7 +2674,7 @@ typing-extensions = ">=4.12.2"
[package.extras]
email = ["email-validator (>=2.0.0)"]
timezone = ["tzdata"]
timezone = ["tzdata ; python_version >= \"3.9\" and platform_system == \"Windows\""]
[[package]]
name = "pydantic-core"
@ -3373,7 +3433,7 @@ crt = ["botocore[crt] (>=1.33.2,<2.0a.0)"]
name = "six"
version = "1.17.0"
description = "Python 2 and 3 compatibility utilities"
optional = true
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
groups = ["main"]
markers = "extra == \"extra-proxy\" or extra == \"proxy\""
@ -3688,7 +3748,7 @@ files = [
]
[package.extras]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
brotli = ["brotli (>=1.0.9) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\""]
h2 = ["h2 (>=4,<5)"]
socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
zstd = ["zstandard (>=0.18.0)"]
@ -3712,7 +3772,7 @@ h11 = ">=0.8"
typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
[package.extras]
standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
[[package]]
name = "uvloop"
@ -3990,11 +4050,11 @@ files = [
]
[package.extras]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)"]
check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1) ; sys_platform != \"cygwin\""]
cover = ["pytest-cov"]
doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-lint"]
enabler = ["pytest-enabler (>=2.2)"]
test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
test = ["big-O", "importlib-resources ; python_version < \"3.9\"", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-ignore-flaky"]
type = ["pytest-mypy"]
[extras]

67
tests/litellm/llms/novita/chat/test_transformation.py Normal file
View file

@ -0,0 +1,67 @@
"""
Unit tests for Novita AI configuration.
These tests validate the NovitaConfig class which extends OpenAIGPTConfig.
Novita AI is an OpenAI-compatible provider with a few customizations.
"""
import os
import sys
from typing import Dict, List, Optional
from unittest.mock import patch
import pytest
sys.path.insert(
0, os.path.abspath("../../../../..")
) # Adds the parent directory to the system path
from litellm.llms.novita.chat.transformation import NovitaConfig
class TestNovitaConfig:
"""Test class for NovitaConfig functionality"""
def test_validate_environment(self):
"""Test that validate_environment adds correct headers"""
config = NovitaConfig()
headers = {}
api_key = "fake-novita-key"
result = config.validate_environment(
headers=headers,
model="novita/meta-llama/llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Hello"}],
optional_params={},
api_key=api_key,
api_base="https://api.novita.ai/v3/openai"
)
# Verify headers
assert result["Authorization"] == f"Bearer {api_key}"
assert result["Content-Type"] == "application/json"
assert result["X-Novita-Source"] == "litellm"
def test_missing_api_key(self):
"""Test error handling when API key is missing"""
config = NovitaConfig()
with pytest.raises(ValueError) as excinfo:
config.validate_environment(
headers={},
model="novita/meta-llama/llama-3.3-70b-instruct",
messages=[{"role": "user", "content": "Hello"}],
optional_params={},
api_key=None,
api_base="https://api.novita.ai/v3/openai"
)
assert "Missing Novita AI API Key" in str(excinfo.value)
def test_inheritance(self):
"""Test proper inheritance from OpenAIGPTConfig"""
config = NovitaConfig()
from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
assert isinstance(config, OpenAIGPTConfig)
assert hasattr(config, "get_supported_openai_params")

71
tests/local_testing/test_completion.py
View file

@ -4658,6 +4658,77 @@ def test_humanloop_completion(monkeypatch):
messages=[{"role": "user", "content": "Tell me a joke."}],
)
def test_completion_novita_ai():
litellm.set_verbose = True
messages = [
{"role": "system", "content": "You're a good bot"},
{
"role": "user",
"content": "Hey",
},
]
from openai import OpenAI
openai_client = OpenAI(api_key="fake-key")
with patch.object(
openai_client.chat.completions, "create", new=MagicMock()
) as mock_call:
try:
completion(
model="novita/meta-llama/llama-3.3-70b-instruct",
messages=messages,
client=openai_client,
api_base="https://api.novita.ai/v3/openai",
)
mock_call.assert_called_once()
# Verify model is passed correctly
assert mock_call.call_args.kwargs["model"] == "meta-llama/llama-3.3-70b-instruct"
# Verify messages are passed correctly
assert mock_call.call_args.kwargs["messages"] == messages
except Exception as e:
pytest.fail(f"Error occurred: {e}")
@pytest.mark.parametrize(
"api_key", ["my-bad-api-key"]
)
def test_completion_novita_ai_dynamic_params(api_key):
try:
litellm.set_verbose = True
messages = [
{"role": "system", "content": "You're a good bot"},
{
"role": "user",
"content": "Hey",
},
]
from openai import OpenAI
openai_client = OpenAI(api_key="fake-key")
with patch.object(
openai_client.chat.completions, "create", side_effect=Exception("Invalid API key")
) as mock_call:
try:
completion(
model="novita/meta-llama/llama-3.3-70b-instruct",
messages=messages,
api_key=api_key,
client=openai_client,
api_base="https://api.novita.ai/v3/openai",
)
pytest.fail(f"This call should have failed!")
except Exception as e:
# This should fail with the mocked exception
assert "Invalid API key" in str(e)
mock_call.assert_called_once()
except Exception as e:
pytest.fail(f"Unexpected error: {e}")
def test_deepseek_reasoning_content_completion():
try: