UiPath · radu-mocanu · Jun 23, 2025 · Jun 19, 2025 · Jun 20, 2025 · Jun 23, 2025
diff --git a/docs/context_grounding.md b/docs/context_grounding.md
@@ -0,0 +1,73 @@
+# Context Grounding
+
+Context Grounding Service allows you to:
+
+- Search through indexed documents using natural language queries
+- Ground LLM responses in your organization's specific information
+- Retrieve context-relevant documents for various applications
+
+
+You will need to create an index in `Context Grounding` to use this feature. To create an index go to organization `Orchestrator` -> the folder where you'd like to create an index -> `Indexes`. There you can create a new index from a storage bucket which you've added documents to. See the full documentation [here](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/about-context-grounding) for more details.
+
+
+## ContextGroundingRetriever
+
+The `ContextGroundingRetriever` is a document retrieval system that uses vector search to efficiently find and retrieve relevant information from your document store.
+
+### Basic Usage
+
+Create a simple retriever by specifying an index name:
+
+```python
+from uipath_llamaindex.retrievers import ContextGroundingRetriever
+
+retriever = ContextGroundingRetriever(index_name = "Company Policy Context")
+print(retriever.retrieve("What is the company policy on remote work?"))
+```
+
+## ContextGroundingQueryEngine
+
+Query engines are interfaces that allows you to ask question over your data. The `ContextGroundingQueryEngine` is a query engine system that leverages the `ContextGroundingRetriever`.
+
+### Basic Usage
+
+Create a simple query engine by specifying an index name and a synthesizer strategy:
+
+```python
+from uipath_llamaindex.query_engines import ContextGroundingQueryEngine
+from llama_index.core.response_synthesizers.type import ResponseMode
+from llama_index.core import get_response_synthesizer
+
+synthesizer = get_response_synthesizer(ResponseMode.SIMPLE_SUMMARIZE)
+query_engine = ContextGroundingQueryEngine(index_name = "Company Policy Context", response_synthesizer=synthesizer)
+print(query_engine.query("What is the company policy on remote work?"))
+```
+
+### Integration with LlamaIndex Tools
+
+You can easily integrate the query engine with LlamaIndex's tool system:
+
+```python
+from uipath_llamaindex.query_engines import ContextGroundingQueryEngine
+from llama_index.core.response_synthesizers.type import ResponseMode
+from llama_index.core import get_response_synthesizer
+
+query_engine = ContextGroundingQueryEngine(
+    index_name="Company Policy Context",
+    response_synthesizer=get_response_synthesizer(ResponseMode.REFINE),
+)
+query_engine_tools = [QueryEngineTool(
+            query_engine=query_engine,
+            metadata=ToolMetadata(
+                name="Company policy",
+                description="Information about general company policy",
+            )
+        )]
+# You can use the tool in your agents
+react_agent = ReActAgent.from_tools(query_engine_tools)
+response = react_agent.chat("Answer user questions as best as you can using the query engine tool.")
+```
+
+
+
+> **HINT:** Check our [travel-helper-RAG-agent sample](https://github.com/UiPath/uipath-llamaindex-python/tree/main/samples/travel-helper-RAG-agent) to see context grounding query engines in action.
diff --git a/docs/sample_images/RAG/create-index-1.png b/docs/sample_images/RAG/create-index-1.png
diff --git a/docs/sample_images/RAG/create-index-2.png b/docs/sample_images/RAG/create-index-2.png
diff --git a/docs/sample_images/RAG/create-storage-bucket-1.png b/docs/sample_images/RAG/create-storage-bucket-1.png
diff --git a/docs/sample_images/RAG/create-storage-bucket-2.png b/docs/sample_images/RAG/create-storage-bucket-2.png
diff --git a/docs/sample_images/RAG/indexes.png b/docs/sample_images/RAG/indexes.png
diff --git a/docs/sample_images/RAG/job-info.png b/docs/sample_images/RAG/job-info.png
diff --git a/docs/sample_images/RAG/run-process-1.png b/docs/sample_images/RAG/run-process-1.png
diff --git a/docs/sample_images/RAG/run-process-2.png b/docs/sample_images/RAG/run-process-2.png
diff --git a/docs/sample_images/RAG/storage_buckets.png b/docs/sample_images/RAG/storage_buckets.png
diff --git a/docs/sample_images/RAG/traces.png b/docs/sample_images/RAG/traces.png
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "uipath-llamaindex"
-version = "0.0.25"
+version = "0.0.26"
 description = "UiPath LlamaIndex SDK"
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"
@@ -90,3 +90,4 @@ name = "testpypi"
 url = "https://test.pypi.org/simple/"
 publish-url = "https://test.pypi.org/legacy/"
 explicit = true
+
diff --git a/samples/simple-hitl-agent/uv.lock b/samples/simple-hitl-agent/uv.lock