[Inference] Use huggingface_hub inference client for TGI adapter (#53)

* Use huggingface_hub inference client for TGI inference

* Update the default value for TGI URL

* Use InferenceClient.text_generation for TGI inference

* Fixes post-review and split TGI adapter into local and Inference Endpoints ones

* Update CLI reference and add typing

* Rename TGI Adapter class

* Use HfApi to get the namespace when not provide in the hf endpoint name

* Remove unecessary method argument

* Improve TGI adapter initialization condition

* Move helper into impl file + fix merging conflicts

llama_toolchain/inference/adapters/tgi/config.py

@@ -0,0 +1,29 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Optional
+
+from llama_models.schema_utils import json_schema_type
+from pydantic import BaseModel, Field
+
+
+@json_schema_type
+class TGIImplConfig(BaseModel):
+    url: Optional[str] = Field(
+        default=None,
+        description="The URL for the local TGI endpoint (e.g., http://localhost:8080)",
+    )
+    api_token: Optional[str] = Field(
+        default=None,
+        description="The HF token for Hugging Face Inference Endpoints (will default to locally saved token if not provided)",
+    )
+    hf_endpoint_name: Optional[str] = Field(
+        default=None,
+        description="The name of the Hugging Face Inference Endpoint : can be either in the format of '{namespace}/{endpoint_name}' (namespace can be the username or organization name) or just '{endpoint_name}' if logged into the same account as the namespace",
+    )
+
+    def is_inference_endpoint(self) -> bool:
+        return self.hf_endpoint_name is not None