fix: revert to main

Author: cosmyo

packages/uipath-llamaindex/.vscode/settings.json

@@ -1,7 +1,7 @@
 # LLMs and Embeddings
 
 UiPath provides pre-configured LLM and embedding classes that handle authentication, routing, and configuration automatically, allowing you to focus on building your agents.
-You do not need to add tokens from OpenAI, usage of these models will consume `Agent Units` on your account.
+You do not need to add API keys from OpenAI, AWS, or Google, usage of these models will consume `Agent Units` on your account.
 
 ## UiPathOpenAI
 
@@ -49,10 +49,10 @@ print(response)
 from uipath_llamaindex.llms import UiPathOpenAI, OpenAIModel
 
 # Use a specific model
-llm = UiPathOpenAI(model=OpenAIModel.GPT_4O_2024_11_20)
+llm = UiPathOpenAI(model=OpenAIModel.GPT_4_1_2025_04_14)
 
 # Or use a model string directly
-llm = UiPathOpenAI(model="gpt-4o-2024-11-20")
+llm = UiPathOpenAI(model="gpt-4.1-2025-04-14")
 ```
 
 ## UiPathOpenAIEmbedding
@@ -97,10 +97,100 @@ embeddings = embed_model.get_text_embedding_batch(texts)
 print(f"Number of embeddings: {len(embeddings)}")
 ```
 
+## UiPathChatBedrock and UiPathChatBedrockConverse
+
+`UiPathChatBedrock` and `UiPathChatBedrockConverse` provide access to AWS Bedrock models through UiPath using the Invoke API and Converse API respectively.
+
+### Installation
+
+These classes require additional dependencies. Install them with:
+
+```bash
+pip install uipath-llamaindex[bedrock]
+# or using uv:
+uv add 'uipath-llamaindex[bedrock]'
+```
+
+### Example Usage
+
+```python
+from uipath_llamaindex.llms.bedrock import UiPathChatBedrockConverse
+from uipath_llamaindex.llms import BedrockModel
+from llama_index.core.llms import ChatMessage
+
+# Create an LLM instance with default settings
+llm = UiPathChatBedrockConverse()
+
+# Or use a specific model
+llm = UiPathChatBedrockConverse(model=BedrockModel.anthropic_claude_sonnet_4_5)
+
+# Create chat messages
+messages = [
+    ChatMessage(role="user", content="Hello"),
+]
+
+# Generate a response
+response = llm.chat(messages)
+print(response)
+```
+
+Similarly, `UiPathChatBedrock` can be used with the Invoke API:
+
+```python
+from uipath_llamaindex.llms.bedrock import UiPathChatBedrock
+from uipath_llamaindex.llms import BedrockModel
+
+llm = UiPathChatBedrock(model=BedrockModel.anthropic_claude_sonnet_4)
+```
+
+Currently, the following models can be used (this list can be updated in the future):
+
+- `anthropic.claude-3-7-sonnet-20250219-v1:0`, `anthropic.claude-sonnet-4-20250514-v1:0`, `anthropic.claude-sonnet-4-5-20250929-v1:0`, `anthropic.claude-haiku-4-5-20251001-v1:0`
+
+## UiPathVertex
+
+`UiPathVertex` provides access to Google Vertex AI (Gemini) models through UiPath.
+
+### Installation
+
+This class requires additional dependencies. Install them with:
+
+```bash
+pip install uipath-llamaindex[vertex]
+# or using uv:
+uv add 'uipath-llamaindex[vertex]'
+```
+
+### Example Usage
+
+```python
+from uipath_llamaindex.llms.vertex import UiPathVertex
+from uipath_llamaindex.llms import GeminiModel
+from llama_index.core.llms import ChatMessage
+
+# Create an LLM instance with default settings
+llm = UiPathVertex()
+
+# Or use a specific model
+llm = UiPathVertex(model=GeminiModel.gemini_2_5_pro)
+
+# Create chat messages
+messages = [
+    ChatMessage(role="user", content="Hello"),
+]
+
+# Generate a response
+response = llm.chat(messages)
+print(response)
+```
+
+Currently, the following models can be used (this list can be updated in the future):
+
+- `gemini-2.0-flash-001`, `gemini-2.5-flash`, `gemini-2.5-pro`
 
 ## Integration with LlamaIndex
 
-Both classes integrate seamlessly with LlamaIndex components:
+These classes integrate seamlessly with LlamaIndex components:
 
 ### Using with Agents
 
@@ -121,7 +211,7 @@ def add(a: int, b: int) -> int:
 # Create agent with UiPath LLM
 agent = ReActAgent(
     tools=[multiply, add],
-    llm=UiPathOpenAI(model=OpenAIModel.GPT_4O_2024_11_20))
+    llm=UiPathOpenAI(model=OpenAIModel.GPT_4_1_2025_04_14))
 
 async def main():
     handler = agent.run("What is 2+(2*4)?")
@@ -151,7 +241,7 @@ index = VectorStoreIndex.from_documents(
 
 # Create query engine with UiPath LLM
 query_engine = index.as_query_engine(
-    llm=UiPathOpenAI(model=OpenAIModel.GPT_4O_2024_11_20)
+    llm=UiPathOpenAI(model=OpenAIModel.GPT_4_1_2025_04_14)
 )
 
 response = query_engine.query("What is machine learning?")

packages/uipath-llamaindex/docs/llms_and_embeddings.md

@@ -1,6 +1,6 @@
 [project]
 name = "uipath-llamaindex"
-version = "0.3.0"
+version = "0.4.1"
 description = "UiPath LlamaIndex SDK"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.11"
@@ -10,8 +10,8 @@ dependencies = [
     "llama-index-embeddings-azure-openai>=0.4.1",
     "llama-index-llms-azure-openai>=0.4.2",
     "openinference-instrumentation-llama-index>=4.3.9",
-    "uipath>=2.4.0, <2.5.0",
-    "uipath-runtime>=0.4.0, <0.5.0",
+    "uipath>=2.5.0, <2.6.0",
+    "uipath-runtime>=0.5.0, <0.6.0",
 ]
 classifiers = [
     "Intended Audience :: Developers",
@@ -58,7 +58,9 @@ dev = [
     "pytest>=7.4.0",
     "pytest-cov>=4.1.0",
     "pytest-mock>=3.11.1",
-    "pre-commit>=4.1.0",
+    "pre-commit>=4.5.1",
+    "filelock>=3.20.3",
+    "virtualenv>=20.36.1",
     "pytest-asyncio>=1.0.0",
     "numpy>=1.24.0",
 ]

packages/uipath-llamaindex/pyproject.toml

@@ -9,7 +9,7 @@
 
 from uipath_llamaindex.models import CreateTaskEvent
 
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI()
 
 
 async def may_research_company(ctx: Context, company_name: str) -> bool:

packages/uipath-llamaindex/samples/action-center-hitl-agent/main.py

@@ -11,7 +11,7 @@
 from llama_index.llms.openai import OpenAI
 
 load_dotenv()
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI()
 
 
 async def may_research_company(ctx: Context, company_name: str) -> bool:

packages/uipath-llamaindex/samples/hitl-runtime-demo/main.py

@@ -9,7 +9,7 @@
 
 from uipath_llamaindex.models import InvokeProcessEvent
 
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI()
 
 
 async def may_research_company(ctx: Context, company_name: str) -> str:

packages/uipath-llamaindex/samples/multi-agent/main.py

@@ -6,7 +6,7 @@
 )
 from llama_index.llms.openai import OpenAI
 
-llm = OpenAI(model="gpt-4o-mini")
+llm = OpenAI()
 
 
 async def may_research_company(ctx: Context, company_name: str) -> bool:

packages/uipath-llamaindex/samples/simple-hitl-agent/main.py

@@ -64,7 +64,7 @@ async def process_query(self, ev: UserQueryEvent) -> AgentResponseEvent:
                 self.agent = FunctionAgent(
                     name="UiPath MCP Agent",
                     description="An agent that can interact with MCP tools",
-                    llm=OpenAI(model="gpt-4o"),
+                    llm=OpenAI(),
                     tools=tools,
                     system_prompt="""You are a helpful assistant.
                     You have access to various tools through MCP (Model Context Protocol).

packages/uipath-llamaindex/samples/simple-remote-mcp-agent/main.py

@@ -24,7 +24,7 @@
 company_policy_files_directory = "sample_data/company_policies"
 personal_preferences_files_directory = "sample_data/personal_preferences"
 
-llm = UiPathOpenAI(model="gpt-4o-2024-11-20")
+llm = UiPathOpenAI()
 
 
 class CustomStartEvent(StartEvent):

packages/uipath-llamaindex/samples/travel-helper-RAG-agent/main.py

@@ -44,7 +44,7 @@ async def handle_async_request(self, request: httpx.Request) -> httpx.Response:
 class UiPathOpenAI(AzureOpenAI):
     def __init__(
         self,
-        model: str | OpenAIModel = OpenAIModel.GPT_4O_MINI_2024_07_18,
+        model: str | OpenAIModel = OpenAIModel.GPT_4_1_2025_04_14,
         api_version: str = "2024-10-21",
         **kwargs: Any,
     ):