Update Functions.py

Functions.py

@@ -1,6 +1,9 @@
 from dotenv import load_dotenv
 import os
 from PyPDF2 import PdfReader
+from docx import Document
+from docx.text.paragraph import Paragraph
+from docx.table import Table
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.vectorstores import Chroma
 from langchain_community.embeddings import OpenAIEmbeddings
@@ -12,6 +15,50 @@ import json
 from Utils import estimate_to_value
 from Utils import is_key_value_present
 
+
+def extract_text_from_file(file):
+    text = file.read().decode("utf-8")
+    return text
+
+
+def process_paragraph(paragraph):
+    # Process the content of the paragraph as needed
+    return paragraph.text
+
+
+def process_table(table):
+    # Process the content of the table as needed
+    text = ""
+    for row in table.rows:
+        for cell in row.cells:
+            text += cell.text
+
+    return text
+
+
+def read_docx(file_path):
+    doc = Document(file_path)
+    data = []
+
+    for element in doc.iter_inner_content():
+        if isinstance(element, Paragraph):
+            data.append(process_paragraph(element))
+        if isinstance(element, Table):
+            data.append(process_table(element))
+
+    return "\n".join(data)
+
+
+def get_pdf_text(pdf):
+    """This function extracts the text from the PDF file"""
+    text = []
+    pdf_reader = PdfReader(pdf)
+    for page in pdf_reader.pages:
+        text.append(page.extract_text())
+
+    return "\n".join(text)
+
+
 class RFPProcessor:
     def __init__(self):
         load_dotenv()
@@ -19,38 +66,73 @@ class RFPProcessor:
         self.chains_obj = LLMChains()
 
     def generate_roadmap(self):
-        
-        roadmap_data = self.chains_obj.roadmap_chain.run({"project_input":st.session_state["estimation_data_json"]})
+
+        roadmap_data = self.chains_obj.roadmap_chain.run(
+            {"project_input": st.session_state["estimation_data_json"]}
+        )
         print(roadmap_data)
         st.session_state["roadmap_data_json"] = roadmap_data
         data = json.loads(roadmap_data)
-        
+
         try:
-          decoded_data = json.loads(roadmap_data)
-          print(decoded_data)
+            decoded_data = json.loads(roadmap_data)
+            print(decoded_data)
         except json.decoder.JSONDecodeError as e:
-          print(f"JSON decoding error: {e}")
-        
-        for phases_data in data['phases']:
-          phase = phases_data["name"]
-          for milestone in phases_data['milestones']:
-               milestone_name = milestone["name"]
-               total_time = milestone["totalTime"]
-               for feature in milestone["features"]:
-                  featue_name = feature["name"]
-                  featue_rationale = feature["rationale"]
-                  featue_effort = feature["effort"]
-                  phase_key_present = is_key_value_present(st.session_state["roadmap_data"], "phases", phase)
-          
-                  if phase_key_present:
-                     milestone_key_present = is_key_value_present(st.session_state["roadmap_data"], "milestones", milestone_name)
-                     if milestone_key_present:
-                         st.session_state.roadmap_data.append({"phases": "","milestones": "","total_time": "","features": featue_name,"rational": featue_rationale,"effort": featue_effort,})
-                     else:
-                         st.session_state.roadmap_data.append({"phases": "","milestones": milestone_name,"total_time": total_time,"features": featue_name,"rational": featue_rationale,"effort": featue_effort,})
-                  else:
-                      st.session_state.roadmap_data.append({"phases": phase,"milestones": milestone_name,"total_time": total_time,"features": featue_name,"rational": featue_rationale,"effort": featue_effort,}) 
-              
+            print(f"JSON decoding error: {e}")
+
+        for phases_data in data["phases"]:
+            phase = phases_data["name"]
+            for milestone in phases_data["milestones"]:
+                milestone_name = milestone["name"]
+                total_time = milestone["totalTime"]
+                for feature in milestone["features"]:
+                    featue_name = feature["name"]
+                    featue_rationale = feature["rationale"]
+                    featue_effort = feature["effort"]
+                    phase_key_present = is_key_value_present(
+                        st.session_state["roadmap_data"], "phases", phase
+                    )
+
+                    if phase_key_present:
+                        milestone_key_present = is_key_value_present(
+                            st.session_state["roadmap_data"],
+                            "milestones",
+                            milestone_name,
+                        )
+                        if milestone_key_present:
+                            st.session_state.roadmap_data.append(
+                                {
+                                    "phases": "",
+                                    "milestones": "",
+                                    "total_time": "",
+                                    "features": featue_name,
+                                    "rational": featue_rationale,
+                                    "effort": featue_effort,
+                                }
+                            )
+                        else:
+                            st.session_state.roadmap_data.append(
+                                {
+                                    "phases": "",
+                                    "milestones": milestone_name,
+                                    "total_time": total_time,
+                                    "features": featue_name,
+                                    "rational": featue_rationale,
+                                    "effort": featue_effort,
+                                }
+                            )
+                    else:
+                        st.session_state.roadmap_data.append(
+                            {
+                                "phases": phase,
+                                "milestones": milestone_name,
+                                "total_time": total_time,
+                                "features": featue_name,
+                                "rational": featue_rationale,
+                                "effort": featue_effort,
+                            }
+                        )
+
         st.session_state["is_roadmap_data_created"] = True
 
     def generate_estimations(self, tech_leads, senior_developers, junior_developers):
@@ -64,9 +146,9 @@ class RFPProcessor:
         }
 
         data = self.chains_obj.estimations_chain.run(inputs)
-        
-        st.session_state["estimation_data_json"]= data
-        
+
+        st.session_state["estimation_data_json"] = data
+
         estimation_json_data = json.loads(data)
 
         for epic_data in estimation_json_data["epics"]:
@@ -90,12 +172,18 @@ class RFPProcessor:
 
     def process_rfp_data(self, project_name, file):
         if project_name and file:
-            loader = PdfReader(file)
-            for i, page in enumerate(loader.pages):
-                content = page.extract_text()
-                if content:
-                    temp = st.session_state["rfp_details"]
-                    st.session_state["rfp_details"] = temp + content
+            if file.name.endswith(".docx"):
+                st.session_state["rfp_details"] = read_docx(file)
+            elif file.name.endswith(".pdf"):
+                st.session_state["rfp_details"] = get_pdf_text(file)
+            else:
+                st.session_state["rfp_details"] = extract_text_from_file(file)
+            # loader = PdfReader(file)
+            # for i, page in enumerate(loader.pages):
+            #     content = page.extract_text()
+            #     if content:
+            #         temp = st.session_state["rfp_details"]
+            #         st.session_state["rfp_details"] = temp + content
 
             text_splitter = CharacterTextSplitter(
                 separator="\n", chunk_size=1000, chunk_overlap=150, length_function=len