diff --git a/docs/my-website/docs/proxy/configs.md b/docs/my-website/docs/proxy/configs.md index 5c97a6601..2379cf4ad 100644 --- a/docs/my-website/docs/proxy/configs.md +++ b/docs/my-website/docs/proxy/configs.md @@ -22,18 +22,22 @@ Set a model alias for your deployments. In the `config.yaml` the model_name parameter is the user-facing name to use for your deployment. -In the config below requests with: +In the config below: +- `model_name`: the name to pass TO litellm from the external client +- `litellm_params.model`: the model string passed to the litellm.completion() function + +E.g.: - `model=vllm-models` will route to `openai/facebook/opt-125m`. - `model=gpt-3.5-turbo` will load balance between `azure/gpt-turbo-small-eu` and `azure/gpt-turbo-small-ca` ```yaml model_list: - - model_name: gpt-3.5-turbo # user-facing model alias + - model_name: gpt-3.5-turbo ### RECEIVED MODEL NAME ### litellm_params: # all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input - model: azure/gpt-turbo-small-eu + model: azure/gpt-turbo-small-eu ### MODEL NAME sent to `litellm.completion()` ### api_base: https://my-endpoint-europe-berri-992.openai.azure.com/ api_key: "os.environ/AZURE_API_KEY_EU" # does os.getenv("AZURE_API_KEY_EU") - rpm: 6 # Rate limit for this deployment: in requests per minute (rpm) + rpm: 6 # [OPTIONAL] Rate limit for this deployment: in requests per minute (rpm) - model_name: bedrock-claude-v1 litellm_params: model: bedrock/anthropic.claude-instant-v1 @@ -43,6 +47,11 @@ model_list: api_base: https://my-endpoint-canada-berri992.openai.azure.com/ api_key: "os.environ/AZURE_API_KEY_CA" rpm: 6 + - model_name: anthropic-claude + litellm_params: + model="bedrock/anthropic.claude-instant-v1" + ### [OPTIONAL] SET AWS REGION ### + aws_region_name="us-east-1" - model_name: vllm-models litellm_params: model: openai/facebook/opt-125m # the `openai/` prefix tells litellm it's openai compatible @@ -58,6 +67,11 @@ litellm_settings: # module level litellm settings - https://github.com/BerriAI/l general_settings: master_key: sk-1234 # [OPTIONAL] Only use this if you to require all calls to contain this key (Authorization: Bearer sk-1234) ``` +:::info + +For more provider-specific info, [go here](../providers/) + +::: #### Step 2: Start Proxy with config diff --git a/docs/my-website/docs/proxy/quick_start.md b/docs/my-website/docs/proxy/quick_start.md index fec578c96..82acfc79b 100644 --- a/docs/my-website/docs/proxy/quick_start.md +++ b/docs/my-website/docs/proxy/quick_start.md @@ -40,115 +40,6 @@ litellm --test This will now automatically route any requests for gpt-3.5-turbo to bigcode starcoder, hosted on huggingface inference endpoints. -### Using LiteLLM Proxy - Curl Request, OpenAI Package, Langchain - - - - -```shell -curl --location 'http://0.0.0.0:8000/chat/completions' \ ---header 'Content-Type: application/json' \ ---data ' { - "model": "gpt-3.5-turbo", - "messages": [ - { - "role": "user", - "content": "what llm are you" - } - ] - } -' -``` - - - -```python -import openai -client = openai.OpenAI( - api_key="anything", - base_url="http://0.0.0.0:8000" -) - -# request sent to model set on litellm proxy, `litellm --model` -response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [ - { - "role": "user", - "content": "this is a test request, write a short poem" - } -]) - -print(response) - -``` - - - -```python -from langchain.chat_models import ChatOpenAI -from langchain.prompts.chat import ( - ChatPromptTemplate, - HumanMessagePromptTemplate, - SystemMessagePromptTemplate, -) -from langchain.schema import HumanMessage, SystemMessage - -chat = ChatOpenAI( - openai_api_base="http://0.0.0.0:8000", # set openai_api_base to the LiteLLM Proxy - model = "gpt-3.5-turbo", - temperature=0.1 -) - -messages = [ - SystemMessage( - content="You are a helpful assistant that im using to make a test request to." - ), - HumanMessage( - content="test from litellm. tell me why it's amazing in 1 sentence" - ), -] -response = chat(messages) - -print(response) -``` - - - - -```python -from langchain.embeddings import OpenAIEmbeddings - -embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") - - -text = "This is a test document." - -query_result = embeddings.embed_query(text) - -print(f"SAGEMAKER EMBEDDINGS") -print(query_result[:5]) - -embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") - -text = "This is a test document." - -query_result = embeddings.embed_query(text) - -print(f"BEDROCK EMBEDDINGS") -print(query_result[:5]) - -embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") - -text = "This is a test document." - -query_result = embeddings.embed_query(text) - -print(f"TITAN EMBEDDINGS") -print(query_result[:5]) -``` - - - - ### Supported LLMs All LiteLLM supported LLMs are supported on the Proxy. Seel all [supported llms](https://docs.litellm.ai/docs/providers) @@ -331,6 +222,113 @@ $ litellm --model command-nightly +### Using LiteLLM Proxy - Curl Request, OpenAI Package, Langchain + + + + +```shell +curl --location 'http://0.0.0.0:8000/chat/completions' \ +--header 'Content-Type: application/json' \ +--data ' { + "model": "gpt-3.5-turbo", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] + } +' +``` + + + +```python +import openai +client = openai.OpenAI( + api_key="anything", + base_url="http://0.0.0.0:8000" +) + +# request sent to model set on litellm proxy, `litellm --model` +response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [ + { + "role": "user", + "content": "this is a test request, write a short poem" + } +]) + +print(response) + +``` + + + +```python +from langchain.chat_models import ChatOpenAI +from langchain.prompts.chat import ( + ChatPromptTemplate, + HumanMessagePromptTemplate, + SystemMessagePromptTemplate, +) +from langchain.schema import HumanMessage, SystemMessage + +chat = ChatOpenAI( + openai_api_base="http://0.0.0.0:8000", # set openai_api_base to the LiteLLM Proxy + model = "gpt-3.5-turbo", + temperature=0.1 +) + +messages = [ + SystemMessage( + content="You are a helpful assistant that im using to make a test request to." + ), + HumanMessage( + content="test from litellm. tell me why it's amazing in 1 sentence" + ), +] +response = chat(messages) + +print(response) +``` + + + + +```python +from langchain.embeddings import OpenAIEmbeddings + +embeddings = OpenAIEmbeddings(model="sagemaker-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") + + +text = "This is a test document." + +query_result = embeddings.embed_query(text) + +print(f"SAGEMAKER EMBEDDINGS") +print(query_result[:5]) + +embeddings = OpenAIEmbeddings(model="bedrock-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") + +text = "This is a test document." + +query_result = embeddings.embed_query(text) + +print(f"BEDROCK EMBEDDINGS") +print(query_result[:5]) + +embeddings = OpenAIEmbeddings(model="bedrock-titan-embeddings", openai_api_base="http://0.0.0.0:8000", openai_api_key="temp-key") + +text = "This is a test document." + +query_result = embeddings.embed_query(text) + +print(f"TITAN EMBEDDINGS") +print(query_result[:5]) +``` + + ## Quick Start - LiteLLM Proxy + Config.yaml