test - making mistral embedding request on proxy

.circleci/config.yml

@@ -202,6 +202,7 @@ jobs:
               -e REDIS_PORT=$REDIS_PORT \
               -e AZURE_FRANCE_API_KEY=$AZURE_FRANCE_API_KEY \
               -e AZURE_EUROPE_API_KEY=$AZURE_EUROPE_API_KEY \
+              -e MISTRAL_API_KEY=$MISTRAL_API_KEY \
               -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
               -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
               -e AWS_REGION_NAME=$AWS_REGION_NAME \

litellm/proxy/proxy_config.yaml

@@ -14,10 +14,9 @@ model_list:
     litellm_params:
       model: openai/*
       api_key: os.environ/OPENAI_API_KEY
-  - model_name: my-triton-model
+  - model_name: mistral-embed
     litellm_params:
-      model: triton/any"
-      api_base: https://exampleopenaiendpoint-production.up.railway.app/triton/embeddings
+      model: mistral/mistral-embed
 
 general_settings:
   master_key: sk-1234

proxy_server_config.yaml

@@ -85,6 +85,9 @@ model_list:
     litellm_params:
       model: openai/*
       api_key: os.environ/OPENAI_API_KEY
+  - model_name: mistral-embed
+    litellm_params:
+      model: mistral/mistral-embed
   - model_name: gpt-instruct # [PROD TEST] - tests if `/health` automatically infers this to be a text completion model
     litellm_params:
       model: text-completion-openai/gpt-3.5-turbo-instruct

tests/test_openai_endpoints.py

@@ -22,6 +22,7 @@ async def generate_key(
         "text-embedding-ada-002",
         "dall-e-2",
         "fake-openai-endpoint-2",
+        "mistral-embed",
     ],
 ):
     url = "http://0.0.0.0:4000/key/generate"
@@ -197,14 +198,14 @@ async def completion(session, key):
         return response
 
 
-async def embeddings(session, key):
+async def embeddings(session, key, model="text-embedding-ada-002"):
     url = "http://0.0.0.0:4000/embeddings"
     headers = {
         "Authorization": f"Bearer {key}",
         "Content-Type": "application/json",
     }
     data = {
-        "model": "text-embedding-ada-002",
+        "model": model,
         "input": ["hello world"],
     }
 
@@ -408,6 +409,9 @@ async def test_embeddings():
         key_2 = key_gen["key"]
         await embeddings(session=session, key=key_2)
 
+        # embedding request with non OpenAI model
+        await embeddings(session=session, key=key, model="mistral-embed")
+
 
 @pytest.mark.asyncio
 async def test_image_generation():