Merge pull request #4145 from BerriAI/litellm_add_embedding_004

[Feat] add VertexAI `vertex_ai/text-embedding-004` , `vertex_ai/text-multilingual-embedding-002 `

docs/my-website/docs/providers/vertex.md

@@ -548,6 +548,8 @@ All models listed [here](https://github.com/BerriAI/litellm/blob/57f37f743886a02
 
 | Model Name               | Function Call                                                                                                                                                      |
 |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| text-embedding-004 | `embedding(model="vertex_ai/text-embedding-004", input)` | 
+| text-multilingual-embedding-002 | `embedding(model="vertex_ai/text-multilingual-embedding-002", input)` | 
 | textembedding-gecko | `embedding(model="vertex_ai/textembedding-gecko", input)` | 
 | textembedding-gecko-multilingual | `embedding(model="vertex_ai/textembedding-gecko-multilingual", input)` | 
 | textembedding-gecko-multilingual@001 | `embedding(model="vertex_ai/textembedding-gecko-multilingual@001", input)` | 

litellm/model_prices_and_context_window_backup.json

@@ -1357,6 +1357,26 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "text-embedding-004": {
+        "max_tokens": 3072,
+        "max_input_tokens": 3072,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
+    "text-multilingual-embedding-002": {
+        "max_tokens": 2048,
+        "max_input_tokens": 2048,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
     "textembedding-gecko": {
         "max_tokens": 3072,
         "max_input_tokens": 3072,

litellm/tests/test_amazing_vertex_completion.py

@@ -810,6 +810,21 @@ def test_vertexai_embedding():
         pytest.fail(f"Error occurred: {e}")
 
 
+def test_vertexai_embedding_embedding_latest():
+    try:
+        load_vertex_ai_credentials()
+        litellm.set_verbose = True
+        response = embedding(
+            model="vertex_ai/text-embedding-004",
+            input=["good morning from litellm", "this is another item"],
+        )
+        print(f"response:", response)
+    except litellm.RateLimitError as e:
+        pass
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 @pytest.mark.asyncio
 async def test_vertexai_aembedding():
     try:

model_prices_and_context_window.json

@@ -1357,6 +1357,26 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "text-embedding-004": {
+        "max_tokens": 3072,
+        "max_input_tokens": 3072,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
+    "text-multilingual-embedding-002": {
+        "max_tokens": 2048,
+        "max_input_tokens": 2048,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
     "textembedding-gecko": {
         "max_tokens": 3072,
         "max_input_tokens": 3072,