From 88b2cfc789665a0ea174a383ae10576fe7225725 Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Tue, 28 Oct 2025 18:41:33 -0700 Subject: [PATCH] docs cleanup --- docs/my-website/docs/providers/vertex.md | 509 ----------------- .../docs/providers/vertex_embedding.md | 511 ++++++++++++++++++ docs/my-website/sidebars.js | 1 + 3 files changed, 512 insertions(+), 509 deletions(-) create mode 100644 docs/my-website/docs/providers/vertex_embedding.md diff --git a/docs/my-website/docs/providers/vertex.md b/docs/my-website/docs/providers/vertex.md index 8e333b69ef7..5df63582446 100644 --- a/docs/my-website/docs/providers/vertex.md +++ b/docs/my-website/docs/providers/vertex.md @@ -2089,515 +2089,6 @@ curl http://0.0.0.0:4000/v1/chat/completions \ | code-gecko@latest| `completion('code-gecko@latest', messages)` | -## **Embedding Models** - -#### Usage - Embedding - - - - -```python -import litellm -from litellm import embedding -litellm.vertex_project = "hardy-device-38811" # Your Project ID -litellm.vertex_location = "us-central1" # proj location - -response = embedding( - model="vertex_ai/textembedding-gecko", - input=["good morning from litellm"], -) -print(response) -``` - - - - - -1. Add model to config.yaml -```yaml -model_list: - - model_name: snowflake-arctic-embed-m-long-1731622468876 - litellm_params: - model: vertex_ai/ - vertex_project: "adroit-crow-413218" - vertex_location: "us-central1" - vertex_credentials: adroit-crow-413218-a956eef1a2a8.json - -litellm_settings: - drop_params: True -``` - -2. Start Proxy - -``` -$ litellm --config /path/to/config.yaml -``` - -3. Make Request using OpenAI Python SDK, Langchain Python SDK - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -response = client.embeddings.create( - model="snowflake-arctic-embed-m-long-1731622468876", - input = ["good morning from litellm", "this is another item"], -) - -print(response) -``` - - - - - -#### Supported Embedding Models -All models listed [here](https://github.com/BerriAI/litellm/blob/57f37f743886a0249f630a6792d49dffc2c5d9b7/model_prices_and_context_window.json#L835) are supported - -| 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)` | -| textembedding-gecko@001 | `embedding(model="vertex_ai/textembedding-gecko@001", input)` | -| textembedding-gecko@003 | `embedding(model="vertex_ai/textembedding-gecko@003", input)` | -| text-embedding-preview-0409 | `embedding(model="vertex_ai/text-embedding-preview-0409", input)` | -| text-multilingual-embedding-preview-0409 | `embedding(model="vertex_ai/text-multilingual-embedding-preview-0409", input)` | -| Fine-tuned OR Custom Embedding models | `embedding(model="vertex_ai/", input)` | - -### Supported OpenAI (Unified) Params - -| [param](../embedding/supported_embedding.md#input-params-for-litellmembedding) | type | [vertex equivalent](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api) | -|-------|-------------|--------------------| -| `input` | **string or List[string]** | `instances` | -| `dimensions` | **int** | `output_dimensionality` | -| `input_type` | **Literal["RETRIEVAL_QUERY","RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION"]** | `task_type` | - -#### Usage with OpenAI (Unified) Params - - - - - -```python -response = litellm.embedding( - model="vertex_ai/text-embedding-004", - input=["good morning from litellm", "gm"] - input_type = "RETRIEVAL_DOCUMENT", - dimensions=1, -) -``` - - - - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -response = client.embeddings.create( - model="text-embedding-004", - input = ["good morning from litellm", "gm"], - dimensions=1, - extra_body = { - "input_type": "RETRIEVAL_QUERY", - } -) - -print(response) -``` - - - - -### Supported Vertex Specific Params - -| param | type | -|-------|-------------| -| `auto_truncate` | **bool** | -| `task_type` | **Literal["RETRIEVAL_QUERY","RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION"]** | -| `title` | **str** | - -#### Usage with Vertex Specific Params (Use `task_type` and `title`) - -You can pass any vertex specific params to the embedding model. Just pass them to the embedding function like this: - -[Relevant Vertex AI doc with all embedding params](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api#request_body) - - - - -```python -response = litellm.embedding( - model="vertex_ai/text-embedding-004", - input=["good morning from litellm", "gm"] - task_type = "RETRIEVAL_DOCUMENT", - title = "test", - dimensions=1, - auto_truncate=True, -) -``` - - - - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -response = client.embeddings.create( - model="text-embedding-004", - input = ["good morning from litellm", "gm"], - dimensions=1, - extra_body = { - "task_type": "RETRIEVAL_QUERY", - "auto_truncate": True, - "title": "test", - } -) - -print(response) -``` - - - -## **Multi-Modal Embeddings** - - -Known Limitations: -- Only supports 1 image / video / image per request -- Only supports GCS or base64 encoded images / videos - -### Usage - - - - -Using GCS Images - -```python -response = await litellm.aembedding( - model="vertex_ai/multimodalembedding@001", - input="gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" # will be sent as a gcs image -) -``` - -Using base 64 encoded images - -```python -response = await litellm.aembedding( - model="vertex_ai/multimodalembedding@001", - input="data:image/jpeg;base64,..." # will be sent as a base64 encoded image -) -``` - - - - -1. Add model to config.yaml -```yaml -model_list: - - model_name: multimodalembedding@001 - litellm_params: - model: vertex_ai/multimodalembedding@001 - vertex_project: "adroit-crow-413218" - vertex_location: "us-central1" - vertex_credentials: adroit-crow-413218-a956eef1a2a8.json - -litellm_settings: - drop_params: True -``` - -2. Start Proxy - -``` -$ litellm --config /path/to/config.yaml -``` - -3. Make Request use OpenAI Python SDK, Langchain Python SDK - - - - - - -Requests with GCS Image / Video URI - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -# # request sent to model set on litellm proxy, `litellm --model` -response = client.embeddings.create( - model="multimodalembedding@001", - input = "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", -) - -print(response) -``` - -Requests with base64 encoded images - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -# # request sent to model set on litellm proxy, `litellm --model` -response = client.embeddings.create( - model="multimodalembedding@001", - input = "data:image/jpeg;base64,...", -) - -print(response) -``` - - - - - -Requests with GCS Image / Video URI -```python -from langchain_openai import OpenAIEmbeddings - -embeddings_models = "multimodalembedding@001" - -embeddings = OpenAIEmbeddings( - model="multimodalembedding@001", - base_url="http://0.0.0.0:4000", - api_key="sk-1234", # type: ignore -) - - -query_result = embeddings.embed_query( - "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" -) -print(query_result) - -``` - -Requests with base64 encoded images - -```python -from langchain_openai import OpenAIEmbeddings - -embeddings_models = "multimodalembedding@001" - -embeddings = OpenAIEmbeddings( - model="multimodalembedding@001", - base_url="http://0.0.0.0:4000", - api_key="sk-1234", # type: ignore -) - - -query_result = embeddings.embed_query( - "data:image/jpeg;base64,..." -) -print(query_result) - -``` - - - - - - - - - -1. Add model to config.yaml -```yaml -default_vertex_config: - vertex_project: "adroit-crow-413218" - vertex_location: "us-central1" - vertex_credentials: adroit-crow-413218-a956eef1a2a8.json -``` - -2. Start Proxy - -``` -$ litellm --config /path/to/config.yaml -``` - -3. Make Request use OpenAI Python SDK - -```python -import vertexai - -from vertexai.vision_models import Image, MultiModalEmbeddingModel, Video -from vertexai.vision_models import VideoSegmentConfig -from google.auth.credentials import Credentials - - -LITELLM_PROXY_API_KEY = "sk-1234" -LITELLM_PROXY_BASE = "http://0.0.0.0:4000/vertex-ai" - -import datetime - -class CredentialsWrapper(Credentials): - def __init__(self, token=None): - super().__init__() - self.token = token - self.expiry = None # or set to a future date if needed - - def refresh(self, request): - pass - - def apply(self, headers, token=None): - headers['Authorization'] = f'Bearer {self.token}' - - @property - def expired(self): - return False # Always consider the token as non-expired - - @property - def valid(self): - return True # Always consider the credentials as valid - -credentials = CredentialsWrapper(token=LITELLM_PROXY_API_KEY) - -vertexai.init( - project="adroit-crow-413218", - location="us-central1", - api_endpoint=LITELLM_PROXY_BASE, - credentials = credentials, - api_transport="rest", - -) - -model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding") -image = Image.load_from_file( - "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" -) - -embeddings = model.get_embeddings( - image=image, - contextual_text="Colosseum", - dimension=1408, -) -print(f"Image Embedding: {embeddings.image_embedding}") -print(f"Text Embedding: {embeddings.text_embedding}") -``` - - - - - -### Text + Image + Video Embeddings - - - - -Text + Image - -```python -response = await litellm.aembedding( - model="vertex_ai/multimodalembedding@001", - input=["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"] # will be sent as a gcs image -) -``` - -Text + Video - -```python -response = await litellm.aembedding( - model="vertex_ai/multimodalembedding@001", - input=["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image -) -``` - -Image + Video - -```python -response = await litellm.aembedding( - model="vertex_ai/multimodalembedding@001", - input=["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image -) -``` - - - - - -1. Add model to config.yaml -```yaml -model_list: - - model_name: multimodalembedding@001 - litellm_params: - model: vertex_ai/multimodalembedding@001 - vertex_project: "adroit-crow-413218" - vertex_location: "us-central1" - vertex_credentials: adroit-crow-413218-a956eef1a2a8.json - -litellm_settings: - drop_params: True -``` - -2. Start Proxy - -``` -$ litellm --config /path/to/config.yaml -``` - -3. Make Request use OpenAI Python SDK, Langchain Python SDK - - -Text + Image - -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -# # request sent to model set on litellm proxy, `litellm --model` -response = client.embeddings.create( - model="multimodalembedding@001", - input = ["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"], -) - -print(response) -``` - -Text + Video -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -# # request sent to model set on litellm proxy, `litellm --model` -response = client.embeddings.create( - model="multimodalembedding@001", - input = ["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"], -) - -print(response) -``` - -Image + Video -```python -import openai - -client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") - -# # request sent to model set on litellm proxy, `litellm --model` -response = client.embeddings.create( - model="multimodalembedding@001", - input = ["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"], -) - -print(response) -``` - - - - - ## **Gemini TTS (Text-to-Speech) Audio Output** :::info diff --git a/docs/my-website/docs/providers/vertex_embedding.md b/docs/my-website/docs/providers/vertex_embedding.md new file mode 100644 index 00000000000..25580935387 --- /dev/null +++ b/docs/my-website/docs/providers/vertex_embedding.md @@ -0,0 +1,511 @@ +import Image from '@theme/IdealImage'; +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# Vertex AI Embedding + +## Usage - Embedding + + + + +```python +import litellm +from litellm import embedding +litellm.vertex_project = "hardy-device-38811" # Your Project ID +litellm.vertex_location = "us-central1" # proj location + +response = embedding( + model="vertex_ai/textembedding-gecko", + input=["good morning from litellm"], +) +print(response) +``` + + + + + +1. Add model to config.yaml +```yaml +model_list: + - model_name: snowflake-arctic-embed-m-long-1731622468876 + litellm_params: + model: vertex_ai/ + vertex_project: "adroit-crow-413218" + vertex_location: "us-central1" + vertex_credentials: adroit-crow-413218-a956eef1a2a8.json + +litellm_settings: + drop_params: True +``` + +2. Start Proxy + +``` +$ litellm --config /path/to/config.yaml +``` + +3. Make Request using OpenAI Python SDK, Langchain Python SDK + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +response = client.embeddings.create( + model="snowflake-arctic-embed-m-long-1731622468876", + input = ["good morning from litellm", "this is another item"], +) + +print(response) +``` + + + + + +#### Supported Embedding Models +All models listed [here](https://github.com/BerriAI/litellm/blob/57f37f743886a0249f630a6792d49dffc2c5d9b7/model_prices_and_context_window.json#L835) are supported + +| 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)` | +| textembedding-gecko@001 | `embedding(model="vertex_ai/textembedding-gecko@001", input)` | +| textembedding-gecko@003 | `embedding(model="vertex_ai/textembedding-gecko@003", input)` | +| text-embedding-preview-0409 | `embedding(model="vertex_ai/text-embedding-preview-0409", input)` | +| text-multilingual-embedding-preview-0409 | `embedding(model="vertex_ai/text-multilingual-embedding-preview-0409", input)` | +| Fine-tuned OR Custom Embedding models | `embedding(model="vertex_ai/", input)` | + +### Supported OpenAI (Unified) Params + +| [param](../embedding/supported_embedding.md#input-params-for-litellmembedding) | type | [vertex equivalent](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api) | +|-------|-------------|--------------------| +| `input` | **string or List[string]** | `instances` | +| `dimensions` | **int** | `output_dimensionality` | +| `input_type` | **Literal["RETRIEVAL_QUERY","RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION"]** | `task_type` | + +#### Usage with OpenAI (Unified) Params + + + + + +```python +response = litellm.embedding( + model="vertex_ai/text-embedding-004", + input=["good morning from litellm", "gm"] + input_type = "RETRIEVAL_DOCUMENT", + dimensions=1, +) +``` + + + + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +response = client.embeddings.create( + model="text-embedding-004", + input = ["good morning from litellm", "gm"], + dimensions=1, + extra_body = { + "input_type": "RETRIEVAL_QUERY", + } +) + +print(response) +``` + + + + +### Supported Vertex Specific Params + +| param | type | +|-------|-------------| +| `auto_truncate` | **bool** | +| `task_type` | **Literal["RETRIEVAL_QUERY","RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION"]** | +| `title` | **str** | + +#### Usage with Vertex Specific Params (Use `task_type` and `title`) + +You can pass any vertex specific params to the embedding model. Just pass them to the embedding function like this: + +[Relevant Vertex AI doc with all embedding params](https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api#request_body) + + + + +```python +response = litellm.embedding( + model="vertex_ai/text-embedding-004", + input=["good morning from litellm", "gm"] + task_type = "RETRIEVAL_DOCUMENT", + title = "test", + dimensions=1, + auto_truncate=True, +) +``` + + + + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +response = client.embeddings.create( + model="text-embedding-004", + input = ["good morning from litellm", "gm"], + dimensions=1, + extra_body = { + "task_type": "RETRIEVAL_QUERY", + "auto_truncate": True, + "title": "test", + } +) + +print(response) +``` + + + +## **Multi-Modal Embeddings** + + +Known Limitations: +- Only supports 1 image / video / image per request +- Only supports GCS or base64 encoded images / videos + +### Usage + + + + +Using GCS Images + +```python +response = await litellm.aembedding( + model="vertex_ai/multimodalembedding@001", + input="gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" # will be sent as a gcs image +) +``` + +Using base 64 encoded images + +```python +response = await litellm.aembedding( + model="vertex_ai/multimodalembedding@001", + input="data:image/jpeg;base64,..." # will be sent as a base64 encoded image +) +``` + + + + +1. Add model to config.yaml +```yaml +model_list: + - model_name: multimodalembedding@001 + litellm_params: + model: vertex_ai/multimodalembedding@001 + vertex_project: "adroit-crow-413218" + vertex_location: "us-central1" + vertex_credentials: adroit-crow-413218-a956eef1a2a8.json + +litellm_settings: + drop_params: True +``` + +2. Start Proxy + +``` +$ litellm --config /path/to/config.yaml +``` + +3. Make Request use OpenAI Python SDK, Langchain Python SDK + + + + + + +Requests with GCS Image / Video URI + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +# # request sent to model set on litellm proxy, `litellm --model` +response = client.embeddings.create( + model="multimodalembedding@001", + input = "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", +) + +print(response) +``` + +Requests with base64 encoded images + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +# # request sent to model set on litellm proxy, `litellm --model` +response = client.embeddings.create( + model="multimodalembedding@001", + input = "data:image/jpeg;base64,...", +) + +print(response) +``` + + + + + +Requests with GCS Image / Video URI +```python +from langchain_openai import OpenAIEmbeddings + +embeddings_models = "multimodalembedding@001" + +embeddings = OpenAIEmbeddings( + model="multimodalembedding@001", + base_url="http://0.0.0.0:4000", + api_key="sk-1234", # type: ignore +) + + +query_result = embeddings.embed_query( + "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" +) +print(query_result) + +``` + +Requests with base64 encoded images + +```python +from langchain_openai import OpenAIEmbeddings + +embeddings_models = "multimodalembedding@001" + +embeddings = OpenAIEmbeddings( + model="multimodalembedding@001", + base_url="http://0.0.0.0:4000", + api_key="sk-1234", # type: ignore +) + + +query_result = embeddings.embed_query( + "data:image/jpeg;base64,..." +) +print(query_result) + +``` + + + + + + + + + +1. Add model to config.yaml +```yaml +default_vertex_config: + vertex_project: "adroit-crow-413218" + vertex_location: "us-central1" + vertex_credentials: adroit-crow-413218-a956eef1a2a8.json +``` + +2. Start Proxy + +``` +$ litellm --config /path/to/config.yaml +``` + +3. Make Request use OpenAI Python SDK + +```python +import vertexai + +from vertexai.vision_models import Image, MultiModalEmbeddingModel, Video +from vertexai.vision_models import VideoSegmentConfig +from google.auth.credentials import Credentials + + +LITELLM_PROXY_API_KEY = "sk-1234" +LITELLM_PROXY_BASE = "http://0.0.0.0:4000/vertex-ai" + +import datetime + +class CredentialsWrapper(Credentials): + def __init__(self, token=None): + super().__init__() + self.token = token + self.expiry = None # or set to a future date if needed + + def refresh(self, request): + pass + + def apply(self, headers, token=None): + headers['Authorization'] = f'Bearer {self.token}' + + @property + def expired(self): + return False # Always consider the token as non-expired + + @property + def valid(self): + return True # Always consider the credentials as valid + +credentials = CredentialsWrapper(token=LITELLM_PROXY_API_KEY) + +vertexai.init( + project="adroit-crow-413218", + location="us-central1", + api_endpoint=LITELLM_PROXY_BASE, + credentials = credentials, + api_transport="rest", + +) + +model = MultiModalEmbeddingModel.from_pretrained("multimodalembedding") +image = Image.load_from_file( + "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png" +) + +embeddings = model.get_embeddings( + image=image, + contextual_text="Colosseum", + dimension=1408, +) +print(f"Image Embedding: {embeddings.image_embedding}") +print(f"Text Embedding: {embeddings.text_embedding}") +``` + + + + + +### Text + Image + Video Embeddings + + + + +Text + Image + +```python +response = await litellm.aembedding( + model="vertex_ai/multimodalembedding@001", + input=["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"] # will be sent as a gcs image +) +``` + +Text + Video + +```python +response = await litellm.aembedding( + model="vertex_ai/multimodalembedding@001", + input=["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image +) +``` + +Image + Video + +```python +response = await litellm.aembedding( + model="vertex_ai/multimodalembedding@001", + input=["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"] # will be sent as a gcs image +) +``` + + + + + +1. Add model to config.yaml +```yaml +model_list: + - model_name: multimodalembedding@001 + litellm_params: + model: vertex_ai/multimodalembedding@001 + vertex_project: "adroit-crow-413218" + vertex_location: "us-central1" + vertex_credentials: adroit-crow-413218-a956eef1a2a8.json + +litellm_settings: + drop_params: True +``` + +2. Start Proxy + +``` +$ litellm --config /path/to/config.yaml +``` + +3. Make Request use OpenAI Python SDK, Langchain Python SDK + + +Text + Image + +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +# # request sent to model set on litellm proxy, `litellm --model` +response = client.embeddings.create( + model="multimodalembedding@001", + input = ["hey", "gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png"], +) + +print(response) +``` + +Text + Video +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +# # request sent to model set on litellm proxy, `litellm --model` +response = client.embeddings.create( + model="multimodalembedding@001", + input = ["hey", "gs://my-bucket/embeddings/supermarket-video.mp4"], +) + +print(response) +``` + +Image + Video +```python +import openai + +client = openai.OpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") + +# # request sent to model set on litellm proxy, `litellm --model` +response = client.embeddings.create( + model="multimodalembedding@001", + input = ["gs://cloud-samples-data/vertex-ai/llm/prompts/landmark1.png", "gs://my-bucket/embeddings/supermarket-video.mp4"], +) + +print(response) +``` + + + \ No newline at end of file diff --git a/docs/my-website/sidebars.js b/docs/my-website/sidebars.js index e467711b59d..789cf690285 100644 --- a/docs/my-website/sidebars.js +++ b/docs/my-website/sidebars.js @@ -519,6 +519,7 @@ const sidebars = { "providers/vertex_ai/videos", "providers/vertex_partner", "providers/vertex_self_deployed", + "providers/vertex_embedding", "providers/vertex_image", "providers/vertex_batch", "providers/vertex_ocr",