feat(vertex): support Vertex AI for generation (#739)

* feat(vertex): support Vertex AI for generation

* style: use `region` instead of `location`

* style: fix format

* style: undo unrelated diffs

Author: badmonster0

Cargo.lock

@@ -117,3 +117,4 @@ aws-sdk-sqs = "1.67.0"
 numpy = "0.25.0"
 infer = "0.19.0"
 serde_with = { version = "3.13.0", features = ["base64"] }
+google-cloud-aiplatform-v1 = "0.4.0"

Cargo.toml

@@ -29,7 +29,7 @@ Ultra performant data transformation framework for AI, with core engine written
 
 </br>
 
-CocoIndex makes it super easy to transform data with AI workloads, and keep source data and target in sync effortlessly.  
+CocoIndex makes it super easy to transform data with AI workloads, and keep source data and target in sync effortlessly.
 
 </br>
 
@@ -39,7 +39,7 @@ CocoIndex makes it super easy to transform data with AI workloads, and keep sour
 
 </br>
 
-Either creating embedding, building knowledge graphs, or any data transformations - beyond traditional SQL. 
+Either creating embedding, building knowledge graphs, or any data transformations - beyond traditional SQL.
 
 ## Exceptional velocity
 Just declare transformation in dataflow with ~100 lines of python
@@ -65,7 +65,7 @@ CocoIndex follows the idea of [Dataflow](https://en.wikipedia.org/wiki/Dataflow_
 **Particularly**, developers don't explicitly mutate data by creating, updating and deleting. They just need to define transformation/formula for a set of source data.
 
 ## Build like LEGO
-Native builtins for different source, targets and transformations. Standardize interface, make it 1-line code switch between different components. 
+Native builtins for different source, targets and transformations. Standardize interface, make it 1-line code switch between different components.
 
 <p align="center">
     <img src="https://cocoindex.io/images/components.svg" alt="CocoIndex Features">

README.md

@@ -33,6 +33,7 @@
     # Submodules
     "_engine",
     "functions",
+    "llm",
     "sources",
     "targets",
     "storages",

python/cocoindex/__init__.py

@@ -45,6 +45,7 @@ class EmbedText(op.FunctionSpec):
     address: str | None = None
     output_dimension: int | None = None
     task_type: str | None = None
+    api_config: llm.VertexAiConfig | None = None
 
 
 class ExtractByLlm(op.FunctionSpec):

python/cocoindex/functions.py

@@ -8,17 +8,29 @@ class LlmApiType(Enum):
     OPENAI = "OpenAi"
     OLLAMA = "Ollama"
     GEMINI = "Gemini"
+    VERTEX_AI = "VertexAi"
     ANTHROPIC = "Anthropic"
     LITE_LLM = "LiteLlm"
     OPEN_ROUTER = "OpenRouter"
     VOYAGE = "Voyage"
     VLLM = "Vllm"
 
 
+@dataclass
+class VertexAiConfig:
+    """A specification for a Vertex AI LLM."""
+
+    kind = "VertexAi"
+
+    project: str
+    region: str | None = None
+
+
 @dataclass
 class LlmSpec:
     """A specification for a LLM."""
 
     api_type: LlmApiType
     model: str
     address: str | None = None
+    api_config: VertexAiConfig | None = None