Spun up app and added pdf uploading functionality with pymupdf

Dockerfile

@@ -18,28 +18,35 @@ ENV PYTHONUNBUFFERED=1
 
 WORKDIR /app
 
-# Create a non-privileged user that the app will run under.
-# See https://docs.docker.com/go/dockerfile-user-best-practices/
-ARG UID=10001
-RUN adduser \
-    --disabled-password \
-    --gecos "" \
-    --home "/nonexistent" \
-    --shell "/sbin/nologin" \
-    --no-create-home \
-    --uid "${UID}" \
-    appuser
-
-# Download dependencies as a separate step to take advantage of Docker's caching.
-# Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
-# Leverage a bind mount to requirements.txt to avoid having to copy them into
-# into this layer.
+# # Create a non-privileged user that the app will run under.
+# # See https://docs.docker.com/go/dockerfile-user-best-practices/
+# ARG UID=10001
+# RUN adduser \
+#     --disabled-password \
+#     --gecos "" \
+#     --home "/nonexistent" \
+#     --shell "/sbin/nologin" \
+#     --no-create-home \
+#     --uid "${UID}" \
+#     appuser
+
+# # Download dependencies as a separate step to take advantage of Docker's caching.
+# # Leverage a cache mount to /root/.cache/pip to speed up subsequent builds.
+# # Leverage a bind mount to requirements.txt to avoid having to copy them into
+# # into this layer.
+
 RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=bind,source=requirements.txt,target=requirements.txt \
     python -m pip install -r requirements.txt
 
-# Switch to the non-privileged user to run the application.
-USER appuser
+# COPY requirements.txt .
+# RUN python -m pip install --no-cache-dir -r requirements.txt
+
+# Install ollama
+RUN curl -fsSL https://ollama.com/install.sh | sh
+
+# # Switch to the non-privileged user to run the application.
+# USER appuser
 
 # Copy the source code into the container.
 COPY . .
@@ -48,4 +55,4 @@ COPY . .
 EXPOSE 8000
 
 # Run the application.
-CMD streamlit run app.py  --server.port 8080
+CMD streamlit run app.py  --server.port 8000

app.py

@@ -0,0 +1,22 @@
+import streamlit as st
+import pymupdf
+from io import StringIO
+
+st.write("## Local RAG \n Get Insights from your documents")
+
+file = st.file_uploader("Upload your Document Here", type=['pdf'])
+
+if file is not None:
+    # doc = pymupdf.open(file)
+    # texts = [page.get_text().encode("utf-8") for page in doc]
+    # texts
+
+    # To read file as bytes:
+    bytes_data = file.getvalue()
+    with open("data/uploaded_file.pdf", "wb") as fp:
+        fp.write(bytes_data)
+        doc = pymupdf.open(fp)
+
+    texts = [page.get_text().encode("utf-8") for page in doc]
+    texts
+

compose.yaml

@@ -11,6 +11,8 @@ services:
   server:
     build:
       context: .
+    volumes:
+      - .:/app
     ports:
       - 8000:8000
 

document_loader.py

@@ -0,0 +1,9 @@
+import pymupdf
+
+doc = pymupdf.open("data/State Machines.pdf")
+
+texts = [page.get_text().encode("utf-8") for page in doc]
+
+print("Done")
+
+# with open("data/State Machines.pdf", "wb", encoding="utf-8") as out:

requirements.txt

@@ -0,0 +1,50 @@
+altair==5.4.1
+anyio==4.4.0
+attrs==24.2.0
+blinker==1.8.2
+cachetools==5.5.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+exceptiongroup==1.2.2
+gitdb==4.0.11
+GitPython==3.1.43
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.2
+idna==3.8
+Jinja2==3.1.4
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+narwhals==1.5.5
+numpy==2.1.0
+ollama==0.3.2
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+protobuf==5.27.4
+pyarrow==17.0.0
+pydeck==0.9.1
+Pygments==2.18.0
+PyMuPDF==1.24.9
+PyMuPDFb==1.24.9
+python-dateutil==2.9.0.post0
+pytz==2024.1
+referencing==0.35.1
+requests==2.32.3
+rich==13.8.0
+rpds-py==0.20.0
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+streamlit==1.38.0
+tenacity==8.5.0
+toml==0.10.2
+tornado==6.4.1
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+watchdog==4.0.2