basic structure

.env.example

@@ -0,0 +1 @@
+MISTRAL_API_KEY=your_mistral_API_key_here

.gitignore

@@ -1 +1,3 @@
-data/documents
+data/documents
+.env
+__pycache__

Dockerfile

@@ -1,20 +1,28 @@
 FROM python:3.13.5-slim
 
+RUN useradd -m -u 1000 user
 WORKDIR /app
 
 RUN apt-get update && apt-get install -y \
     build-essential \
     curl \
     git \
+    poppler-utils \
     && rm -rf /var/lib/apt/lists/*
 
-COPY requirements.txt ./
-COPY src/ ./src/
+COPY --chown=user requirements.txt ./
+COPY --chown=user .env* ./
 
 RUN pip3 install -r requirements.txt
 
 EXPOSE 8501
+COPY --chown=user . /app
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
 
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

requirements.txt

@@ -1,3 +1,5 @@
-altair
 pandas
-streamlit
+streamlit
+dotenv
+mistralai
+pdf2image

src/bon_livraison.py

@@ -0,0 +1,33 @@
+SYSTEM_PROMPT = """
+Extract data in json format
+"""
+
+def extract_from_bl (client, document_source):
+  model = "mistral-medium-2508" # Mistral Medium 3.1
+
+  messages = [
+    {
+      "role": "system",
+      "content": SYSTEM_PROMPT,
+    },
+    {
+      "role": "user",
+      "content": [
+          {
+              "type": "text",
+              "text": "Extract data from this document"
+          },
+          document_source
+      ]
+    }
+  ]
+
+  chat_response = client.chat.complete(
+      model=model,
+      messages=messages,
+      response_format = {
+        "type": "json_object" #, "json_schema": JSON_SCHEMA
+    }
+  )
+
+  return chat_response.choices[0].message.content

src/streamlit_app.py

@@ -2,39 +2,65 @@ import altair as alt
 import numpy as np
 import pandas as pd
 import streamlit as st
+from dotenv import load_dotenv
+import os
+from mistralai import Mistral
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+from util import display_pdf, upload_pdf
+from bon_livraison import extract_from_bl
+
+load_dotenv()
+
+MISTRAL_API_KEY = os.environ.get("MISTRAL_API_KEY")
+
+def main():
+  """
+  Main function to run the Streamlit app.
+  """
+  
+  # Sidebar: Authentication for Mistral API
+  if not MISTRAL_API_KEY:
+    api_key = st.sidebar.text_input("Mistral API Key", type="password")
+  else:
+    api_key = MISTRAL_API_KEY
+  
+  if not api_key:
+    st.warning("Enter API key to continue")
+    return
+    
+  # Initialize Mistral API client
+  client = Mistral(api_key=api_key)
+
+  uploaded_file = st.file_uploader("Choisissez un PDF", type=["pdf"])
+
+  document_source = None
+
+  if uploaded_file:
+    content = uploaded_file.read()
+    preview_content = uploaded_file
+
+    # Display the uploaded PDF
+    display_pdf(content)
+    
+    # Prepare document source for OCR processing
+    document_source = {
+        "type": "document_url",
+        "document_url": upload_pdf(client, content, uploaded_file.name)
+    }
+    content_type = "pdf"
+
+  if document_source and st.button("Générer les données au format JSON"):
+    # Process the document when the user clicks the button
+    with st.spinner("Extracting JSON content..."):
+      try:
+        response = extract_from_bl(client, document_source)
+
+        with st.expander("Response"):
+          st.json(response)
+
+      except Exception as e:
+        # Display an error message if processing fails
+        st.error(f"Processing error: {str(e)}")
+  
+if __name__ == "__main__":
+  main()

src/util.py

@@ -0,0 +1,48 @@
+from pdf2image import convert_from_bytes
+import streamlit as st
+import os
+import tempfile
+
+def display_pdf(content: bytes):
+  try:
+    images = convert_from_bytes(content)
+    for i, image in enumerate(images):
+      st.image(image, caption=f"Page {i+1}", use_container_width=True)
+  except Exception as e:
+    st.error(f"Impossible d'afficher le PDF : {e}")
+    st.download_button(
+      label="📥 Télécharger le PDF",
+      data=content,
+      file_name="document.pdf",
+      mime="application/pdf"
+    )
+
+def upload_pdf(client, content, filename):
+    """
+    Uploads a PDF to Mistral's API and retrieves a signed URL for processing.
+  
+    Args:
+        client (Mistral): Mistral API client instance.
+        content (bytes): The content of the PDF file.
+        filename (str): The name of the PDF file.
+    Returns:
+        str: Signed URL for the uploaded PDF.
+    """
+    with tempfile.TemporaryDirectory() as temp_dir:
+      temp_path = os.path.join(temp_dir, filename)
+  
+      with open(temp_path, "wb") as tmp:
+        tmp.write(content)
+  
+      try:
+        with open(temp_path, "rb") as file_obj:
+          file_upload = client.files.upload(
+            file={"file_name": filename, "content": file_obj},
+            purpose="ocr"
+          )
+    
+        signed_url = client.files.get_signed_url(file_id=file_upload.id)
+        return signed_url.url
+      finally:
+        if os.path.exists(temp_path):
+          os.remove(temp_path)