Docker stuff

.dockerignore

@@ -0,0 +1,16 @@
+.git
+.gitignore
+README.md
+.env
+.DS_Store
+chromadb/
+chroma_db/
+raggr-frontend/node_modules/
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+.venv/
+venv/
+.pytest_cache/

Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.13-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy dependency files
+COPY pyproject.toml ./
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -e .
+
+# Copy application code
+COPY *.py ./
+
+# Create ChromaDB directory
+RUN mkdir -p /app/chromadb
+
+# Expose port
+EXPOSE 8080
+
+# Set environment variables
+ENV PYTHONPATH=/app
+ENV CHROMADB_PATH=/app/chromadb
+
+# Run the Flask application
+CMD ["python", "app.py"]

app.py

@@ -1,6 +1,6 @@
 import os
 
-from flask import Flask, request, jsonify, render_template
+from flask import Flask, request, jsonify, render_template, send_from_directory
 
 from main import consult_simba_oracle
 
@@ -30,4 +30,8 @@ def query():
 def webhook():
     data = request.get_json()
     print(data)
+    return jsonify({"status": "received"})
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8080, debug=True)
 

docker-compose.yml

@@ -0,0 +1,36 @@
+version: '3.8'
+
+services:
+  raggr:
+    build: .
+    ports:
+      - "8080:8080"
+    environment:
+      - PAPERLESS_TOKEN=${PAPERLESS_TOKEN}
+      - BASE_URL=${BASE_URL}
+      - OLLAMA_URL=${OLLAMA_URL:-http://ollama:11434}
+      - CHROMADB_PATH=/app/chromadb
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+    volumes:
+      - chromadb_data:/app/chromadb
+    depends_on:
+      - ollama
+    networks:
+      - raggr-network
+
+  ollama:
+    image: ollama/ollama:latest
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama_data:/root/.ollama
+    networks:
+      - raggr-network
+
+volumes:
+  chromadb_data:
+  ollama_data:
+
+networks:
+  raggr-network:
+    driver: bridge

main.py

@@ -132,9 +132,12 @@ def consult_oracle(input: str, collection):
         # model="gemma3n:e4b",
         # prompt=f"You are a helpful assistant that understandings veterinary terms. Using the following data, help answer the user's query by providing as many details as possible.  Using this data: {results}. Respond to this prompt: {input}",
     # )
-    response = openai_client.responses.create(
+    response = openai_client.chat.completions.create(
         model="gpt-4o-mini",
-        input=f"You are a helpful assistant that understandings veterinary terms. Using the following data, help answer the user's query by providing as many details as possible.  Using this data: {results}. Respond to this prompt: {input}",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant that understands veterinary terms."},
+            {"role": "user", "content": f"Using the following data, help answer the user's query by providing as many details as possible. Using this data: {results}. Respond to this prompt: {input}"}
+        ]
     )
     llm_end = time.time()
     print(f"LLM generation took {llm_end - llm_start:.2f} seconds")
@@ -142,7 +145,7 @@ def consult_oracle(input: str, collection):
     total_time = time.time() - start_time
     print(f"Total consult_oracle execution took {total_time:.2f} seconds")
 
-    return response.output_text
+    return response.choices[0].message.content
 
 
 def paperless_workflow(input):