- added three iwm articles as test data

- added simple webview and FastAPI server

README.md

@@ -4,12 +4,16 @@ Minimal RAG implementation with LangChain, Ollama, and FAISS.
 
 ## Dependencies
 
-Only 5 packages:
 - `langchain` - Core framework
+- `langchain-community` - Community integrations (loaders, vectorstores)
 - `langchain-ollama` - Ollama integration
+- `langchain-text-splitters` - Text splitting utilities
+- `langchain-huggingface` - HuggingFace embeddings
 - `faiss-cpu` - Vector search
 - `sentence-transformers` - Embeddings
 - `pypdf` - PDF loading
+- `fastapi` - Web server and API
+- `uvicorn` - ASGI server
 
 ## Installation
 
@@ -54,6 +58,16 @@ Run:
 python local_rag.py
 ```
 
+## Chat GUI (FastAPI)
+
+A simple web chat interface is included. Start the server:
+
+```bash
+uvicorn server:app --reload
+```
+
+Then open [http://localhost:8000](http://localhost:8000) in your browser. The chat view uses the same RAG system: your messages are answered using the vector store and Ollama. Ensure your vector store is populated (e.g. by running the document-add steps in `local_rag.py` once) and that Ollama is running.
+
 ## How it works
 
 1. **Load documents** - PDFs or text files

local_rag.py

@@ -5,14 +5,14 @@ Minimal dependencies, simple code
 import os
 from pathlib import Path
 from langchain_community.document_loaders import PyPDFLoader, TextLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_ollama import ChatOllama
 
 
 class LocalRAG:
-    def __init__(self, vectorstore_path="./vectorstore", ollama_model="llama2"):
+    def __init__(self, vectorstore_path="./vectorstore", ollama_model="mistral:7b"):
         """Initialize local RAG system"""
         self.vectorstore_path = vectorstore_path
         self.ollama_model = ollama_model
@@ -97,6 +97,42 @@ class LocalRAG:
         self.vectorstore.save_local(self.vectorstore_path)
         print(f"Vector store saved to {self.vectorstore_path}")
     
+    def list_documents(self):
+        """List all documents in the vector store"""
+        if self.vectorstore is None:
+            print("No documents in vector store.")
+            return []
+        
+        # Get all documents from the vector store
+        # We'll retrieve a large number to get all documents
+        all_docs = self.vectorstore.similarity_search("", k=10000)  # Large k to get all
+        
+        # Extract unique document sources from metadata
+        documents = {}
+        for doc in all_docs:
+            source = doc.metadata.get('source', 'Unknown')
+            if source not in documents:
+                documents[source] = {
+                    'source': source,
+                    'chunks': 0,
+                    'page': doc.metadata.get('page', None)
+                }
+            documents[source]['chunks'] += 1
+        
+        # Convert to list and sort
+        doc_list = list(documents.values())
+        doc_list.sort(key=lambda x: x['source'])
+        
+        print(f"\nDocuments in vector store ({len(doc_list)} unique documents):")
+        print("-" * 60)
+        for doc_info in doc_list:
+            print(f"  - {doc_info['source']}")
+            print(f"    Chunks: {doc_info['chunks']}")
+            if doc_info['page'] is not None:
+                print(f"    Page: {doc_info['page']}")
+        
+        return doc_list
+    
     def query(self, question, k=4):
         """Query the RAG system"""
         if self.vectorstore is None:
@@ -134,21 +170,25 @@ def main():
     print("=" * 60)
     
     # Initialize
-    rag = LocalRAG(ollama_model="llama2")
+    rag = LocalRAG(ollama_model="mistral:7b")
     
     # Add documents (uncomment and add your file paths)
-    rag.add_documents([
-         "diverses/local_rag/test1.pdf",
-         "diverses/local_rag/test2.txt"
-    ])
+    # rag.add_documents([
+    #     "data/dok1.pdf",
+    #     "data/dok2.pdf",
+    #     "data/dok3.pdf"
+    # ])
+    
+    # List documents
+    rag.list_documents()
     
     # Query
-    # question = "What is this document about?"
-    # answer = rag.query(question)
-    # print(f"\nQuestion: {question}")
-    # print(f"Answer: {answer}")
+    question = "What do the documents say about modality for perceived message perception?"
+    answer = rag.query(question)
+    print(f"\nQuestion: {question}")
+    print(f"Answer: {answer}")
     
-    print("\nSetup complete! Uncomment the code above to add documents and query.")
+    # print("\nSetup complete! Uncomment the code above to add documents and query.")
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1,5 +1,11 @@
 langchain
+langchain-community
 langchain-ollama
+langchain-text-splitters
+langchain-huggingface
 faiss-cpu
 sentence-transformers
 pypdf
+numpy<2.0
+fastapi
+uvicorn[standard]

server.py

@@ -0,0 +1,60 @@
+"""
+FastAPI server for Local RAG with chat GUI.
+Run with: uvicorn server:app --reload
+"""
+from pathlib import Path
+
+from fastapi import FastAPI, HTTPException
+from fastapi.responses import HTMLResponse
+from pydantic import BaseModel
+
+from local_rag import LocalRAG
+
+# Initialize RAG once at startup
+VECTORSTORE_PATH = "./vectorstore"
+OLLAMA_MODEL = "mistral:7b"
+rag = LocalRAG(vectorstore_path=VECTORSTORE_PATH, ollama_model=OLLAMA_MODEL)
+
+app = FastAPI(title="Local RAG Chat", version="1.0.0")
+
+
+class ChatRequest(BaseModel):
+    message: str
+
+
+class ChatResponse(BaseModel):
+    answer: str
+    error: str | None = None
+
+
+@app.get("/", response_class=HTMLResponse)
+def chat_view():
+    """Serve the chat GUI."""
+    html_path = Path(__file__).parent / "templates" / "chat.html"
+    if not html_path.exists():
+        raise HTTPException(status_code=500, detail="Chat template not found")
+    return HTMLResponse(content=html_path.read_text(encoding="utf-8"))
+
+
+@app.post("/api/chat", response_model=ChatResponse)
+def chat(request: ChatRequest):
+    """Handle a chat message and return the RAG answer."""
+    if not request.message or not request.message.strip():
+        return ChatResponse(answer="", error="Message cannot be empty")
+    try:
+        answer = rag.query(request.message.strip())
+        return ChatResponse(answer=answer)
+    except Exception as e:
+        return ChatResponse(answer="", error=str(e))
+
+
+@app.get("/api/health")
+def health():
+    """Health check and vector store status."""
+    has_docs = rag.vectorstore is not None
+    return {"status": "ok", "vectorstore_loaded": has_docs}
+
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

templates/chat.html

@@ -0,0 +1,209 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8" />
+  <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+  <title>Local RAG Chat</title>
+  <style>
+    * { box-sizing: border-box; }
+    body {
+      font-family: "SF Mono", "Consolas", "Monaco", monospace;
+      margin: 0;
+      min-height: 100vh;
+      background: #0f0f12;
+      color: #e4e4e7;
+      display: flex;
+      flex-direction: column;
+    }
+    header {
+      padding: 1rem 1.5rem;
+      border-bottom: 1px solid #27272a;
+      background: #18181b;
+    }
+    header h1 {
+      margin: 0;
+      font-size: 1rem;
+      font-weight: 600;
+      letter-spacing: 0.02em;
+    }
+    header p {
+      margin: 0.25rem 0 0;
+      font-size: 0.75rem;
+      color: #71717a;
+    }
+    #messages {
+      flex: 1;
+      overflow-y: auto;
+      padding: 1.5rem;
+      display: flex;
+      flex-direction: column;
+      gap: 1rem;
+    }
+    .msg {
+      max-width: 85%;
+      padding: 0.75rem 1rem;
+      border-radius: 8px;
+      font-size: 0.9rem;
+      line-height: 1.5;
+      white-space: pre-wrap;
+      word-break: break-word;
+    }
+    .msg.user {
+      align-self: flex-end;
+      background: #3f3f46;
+      color: #fafafa;
+    }
+    .msg.assistant {
+      align-self: flex-start;
+      background: #27272a;
+      border: 1px solid #3f3f46;
+    }
+    .msg.error {
+      background: #451a1a;
+      border: 1px solid #7f1d1d;
+      color: #fecaca;
+    }
+    .msg .label {
+      font-size: 0.7rem;
+      text-transform: uppercase;
+      letter-spacing: 0.05em;
+      color: #71717a;
+      margin-bottom: 0.5rem;
+      display: block;
+    }
+    #input-area {
+      padding: 1rem 1.5rem 1.5rem;
+      border-top: 1px solid #27272a;
+      background: #18181b;
+    }
+    #input-row {
+      display: flex;
+      gap: 0.5rem;
+      align-items: flex-end;
+    }
+    #input {
+      flex: 1;
+      min-height: 44px;
+      max-height: 160px;
+      padding: 0.6rem 1rem;
+      font: inherit;
+      font-size: 0.9rem;
+      color: #e4e4e7;
+      background: #27272a;
+      border: 1px solid #3f3f46;
+      border-radius: 8px;
+      resize: none;
+      outline: none;
+    }
+    #input::placeholder { color: #71717a; }
+    #input:focus { border-color: #52525b; }
+    #send {
+      padding: 0.6rem 1.2rem;
+      font: inherit;
+      font-size: 0.85rem;
+      font-weight: 500;
+      color: #0f0f12;
+      background: #e4e4e7;
+      border: none;
+      border-radius: 8px;
+      cursor: pointer;
+    }
+    #send:hover { background: #fafafa; }
+    #send:disabled {
+      opacity: 0.5;
+      cursor: not-allowed;
+    }
+    .loading {
+      align-self: flex-start;
+      padding: 0.5rem 1rem;
+      font-size: 0.8rem;
+      color: #71717a;
+    }
+  </style>
+</head>
+<body>
+  <header>
+    <h1>Local RAG Chat</h1>
+    <p>Ask questions about your documents. Answers are generated from the vector store + Ollama.</p>
+  </header>
+
+  <div id="messages"></div>
+
+  <div id="input-area">
+    <div id="input-row">
+      <textarea id="input" rows="1" placeholder="Ask a question…" autofocus></textarea>
+      <button type="button" id="send">Send</button>
+    </div>
+  </div>
+
+  <script>
+    const messagesEl = document.getElementById('messages');
+    const inputEl = document.getElementById('input');
+    const sendBtn = document.getElementById('send');
+
+    function appendMessage(role, text, isError = false) {
+      const div = document.createElement('div');
+      div.className = 'msg ' + (isError ? 'error' : role);
+      const label = role === 'user' ? 'You' : 'RAG';
+      div.innerHTML = '<span class="label">' + label + '</span>' + escapeHtml(text);
+      messagesEl.appendChild(div);
+      messagesEl.scrollTop = messagesEl.scrollHeight;
+    }
+
+    function escapeHtml(s) {
+      const div = document.createElement('div');
+      div.textContent = s;
+      return div.innerHTML;
+    }
+
+    function setLoading(show) {
+      if (show) {
+        const el = document.createElement('div');
+        el.className = 'loading';
+        el.id = 'loading-dot';
+        el.textContent = 'Thinking…';
+        messagesEl.appendChild(el);
+        messagesEl.scrollTop = messagesEl.scrollHeight;
+      } else {
+        const el = document.getElementById('loading-dot');
+        if (el) el.remove();
+      }
+      sendBtn.disabled = show;
+    }
+
+    async function send() {
+      const text = inputEl.value.trim();
+      if (!text) return;
+      inputEl.value = '';
+      appendMessage('user', text);
+
+      setLoading(true);
+      try {
+        const res = await fetch('/api/chat', {
+          method: 'POST',
+          headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify({ message: text })
+        });
+        const data = await res.json();
+        setLoading(false);
+        if (data.error) {
+          appendMessage('assistant', data.error, true);
+        } else {
+          appendMessage('assistant', (data.answer || '(No response)').trim());
+        }
+      } catch (err) {
+        setLoading(false);
+        appendMessage('assistant', 'Request failed: ' + err.message, true);
+      }
+    }
+
+    sendBtn.addEventListener('click', send);
+    inputEl.addEventListener('keydown', (e) => {
+      if (e.key === 'Enter' && !e.shiftKey) {
+        e.preventDefault();
+        send();
+      }
+    });
+  </script>
+</body>
+</html>