cleanup; readme

README.md

@@ -8,3 +8,77 @@ pinned: false
 ---
 
 
+# ChatFed Retriever - MCP Server
+
+A semantic document retrieval and reranking service designed for ChatFed RAG (Retrieval-Augmented Generation) pipelines. This module serves as an **MCP (Model Context Protocol) server** that retrieves semantically similar documents from vector databases with optional cross-encoder reranking.
+
+## MCP Endpoint
+
+The main MCP function is `retrieve_mcp` which provides a top_k retrieval and reranking function when properly connected to an external vector database.
+
+**Parameters**:
+- `query` (str, required): The search query text
+- `reports_filter` (str, optional): Comma-separated list of specific report filenames
+- `sources_filter` (str, optional): Filter by document source type
+- `subtype_filter` (str, optional): Filter by document subtype  
+- `year_filter` (str, optional): Comma-separated list of years to filter by
+
+**Returns**: List of dictionaries containing:
+- `answer`: Document content
+- `answer_metadata`: Document metadata
+- `score`: Relevance score [disabled when reranker used]
+
+
+```python
+from gradio_client import Client
+
+client = Client("https://mtyrrell-chatfed-retriever.hf.space/")
+result = client.predict(
+		query="...",
+		reports_filter="",
+		sources_filter="",
+		subtype_filter="",
+		year_filter="",
+		api_name="/retrieve_mcp"
+)
+print(result)
+```
+
+## ⚙️ Configuration
+
+### Vector Store Configuration
+1. Set your data source according to the provider
+2. Set the embedding model to match the data source
+3. Set the retriever parameters
+4. [Optional] Set the reranker parameters
+5. Run the app:
+
+```bash
+docker build -t chatfed-retriever .
+docker run -p 7860:7860 chatfed-retriever
+```
+
+6. Test connection
+
+```python
+from gradio_client import Client
+
+def test_retrieve_mcp():
+    client = Client("ENTER CONTAINER URL")
+    
+    # Make a simple query
+    result = client.predict(
+        query="Return all audit reports relating to climate change?",
+        reports_filter="",
+        sources_filter="",
+        subtype_filter="",
+        year_filter="",
+        api_name="/retrieve_mcp"
+    )
+    
+    print(result)
+
+if __name__ == "__main__":
+    test_retrieve_mcp()
+```
+

app/main.py

@@ -93,8 +93,8 @@ def retrieve_ui(query, reports_filter="", sources_filter="", subtype_filter="",
 
 # Create the Gradio interface with Blocks to support both UI and MCP
 with gr.Blocks() as ui:
-    gr.Markdown("# RAG Retrieval Service UI")
-    gr.Markdown("Retrieves semantically similar documents from vector database. Intended for use in RAG pipelines as an MCP server.")
+    gr.Markdown("# ChatFed Retrieval/Reranker Module")
+    gr.Markdown("Retrieves semantically similar documents from vector database and reranks. Intended for use in RAG pipelines as an MCP server with other ChatFed modules.")
     
     with gr.Row():
         with gr.Column():