Update app.py

app.py

@@ -3,6 +3,8 @@ import json
 import yaml
 import httpx
 from transformers import pipeline
+import fitz  # PyMuPDF
+import docx  # python-docx for handling doc/docx files
 import logging
 
 # Initialize the Hugging Face model pipeline (using text generation model for simplicity)
@@ -12,7 +14,6 @@ llm_model = pipeline('text-generation', model="bigscience/bloom-560m")
 logging.basicConfig(filename='api_client.log', level=logging.INFO, 
                     format='%(asctime)s - %(levelname)s - %(message)s')
 
-
 def parse_api_spec(api_spec_content):
     """
     This function parses the uploaded API specification and returns endpoints and their parameters.
@@ -79,18 +80,50 @@ def use_llm_to_extract(api_spec):
     
     return response[0]['generated_text']
 
+def read_pdf(file):
+    """
+    Extracts text from PDF file using PyMuPDF (fitz).
+    """
+    doc = fitz.open(stream=file.read(), filetype="pdf")
+    text = ""
+    for page in doc:
+        text += page.get_text()
+    return text
+
+def read_docx(file):
+    """
+    Extracts text from DOC/DOCX file using python-docx.
+    """
+    doc = docx.Document(file)
+    text = "\n".join([para.text for para in doc.paragraphs])
+    return text
+
 def main():
     st.title("API Spec Uploader and Python Interface Generator")
 
     # Upload API Spec File
-    uploaded_file = st.file_uploader("Upload API Spec (JSON or YAML)", type=["json", "yaml"])
+    uploaded_file = st.file_uploader("Upload API Spec (JSON, YAML, PDF, DOC)", type=["json", "yaml", "pdf", "docx"])
 
     if uploaded_file is not None:
-        api_spec_content = uploaded_file.read().decode("utf-8")
+        file_type = uploaded_file.type
+
+        if file_type == "application/json":
+            api_spec_content = uploaded_file.read().decode("utf-8")
+        elif file_type == "application/x-yaml":
+            api_spec_content = uploaded_file.read().decode("utf-8")
+        elif file_type == "application/pdf":
+            # Extract text from PDF
+            api_spec_content = read_pdf(uploaded_file)
+        elif file_type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+            # Extract text from DOCX
+            api_spec_content = read_docx(uploaded_file)
+        else:
+            st.error("Unsupported file format.")
+            return
 
         # Display API Spec
         st.subheader("Uploaded API Specification")
-        st.code(api_spec_content, language="json" if uploaded_file.type == "application/json" else "yaml")
+        st.code(api_spec_content, language="json" if file_type == "application/json" else "yaml")
 
         # Extract API endpoints and parameters using LLM
         with st.spinner('Extracting API information using Hugging Face LLM...'):