Phase 2/HuyDN: add result_cv_matching function

.gitignore

@@ -2,3 +2,6 @@ venv/
 .env
 __pycache__/
 credentials/
+data/CV
+data/JD
+data/QUESTION

app/modules/crud_question_test/__init__.py

@@ -20,7 +20,7 @@ async def add_question_test(description: str, role: str, file_question_tests: An
         # check if file is pdf or json
         if file_question_tests.content_type == "application/pdf":
             # create a new document
-            if create_question_test({"description": description, "role": role, "question_tests": file_question_tests}):
+            if create_question_test({"question_tests_description": description, "question_tests_role": role, "question_tests_url": file_question_tests}):
                 return {"message": "Question test added successfully"}
             else:
                 return {"message": "Error"}

app/modules/matching_cv/__init__.py

@@ -1,8 +1,36 @@
-from fastapi import APIRouter, UploadFile, File
-from typing import Annotated
+import docx
+
+from fastapi import APIRouter
+from app.modules.matching_cv.models.match_cv_jd_model import Match_JD_CV_Model
+
+from app.modules.matching_cv.models.matching_cv_logic import result_matching_cv_jd, load_jd_from_id
 
 cvmatching_router = APIRouter(prefix="/cvmatching", tags=["cvmatching"])
 
 @cvmatching_router.get("/")
 async def index():
-    return {"message": "Welcome to CV matching page"}
+    return {"message": "Welcome to CV matching page"}
+
+@cvmatching_router.post("/matching")
+# only upload .pdf or .docx file
+async def matching_cv_jd(
+    jd_upload: Match_JD_CV_Model.jd = Match_JD_CV_Model.jd_default, 
+    cv_upload: Match_JD_CV_Model.cv = Match_JD_CV_Model.cv_default):
+    try:
+        # take jd_upload and cv_upload type file
+        jd_upload_type = jd_upload.filename.split(".")[-1]
+        cv_upload_type = cv_upload.filename.split(".")[-1]
+        if jd_upload_type in ["txt"] and cv_upload_type in ["pdf", "docx"]:
+            jd_text =  jd_upload.file.read().decode("utf-8")
+            if cv_upload_type == "docx":
+                cv_text = docx.Document(cv_upload.file).paragraphs
+                cv_text = "\n".join([i.text for i in cv_text])
+            elif cv_upload_type == "pdf":
+                return {"message": "This feature is not available yet"}
+            # check matching cv and jd
+            result = result_matching_cv_jd(cv_text, jd_text)
+            return {"result": result}
+        else:
+            return {"message": "Please upload only .txt for JD. And .pdf or .docx file for CV"}
+    except Exception as e:
+        return {"Error": str(e)}

app/modules/matching_cv/models/match_cv_jd_model.py

@@ -0,0 +1,7 @@
+from fastapi import APIRouter, UploadFile, File
+
+class Match_JD_CV_Model:
+    jd = UploadFile
+    jd_default = File(..., description="Upload JD file", media_type=["text/plain"])
+    cv = UploadFile
+    cv_default = File(..., description="Upload CV file", media_type=["application/pdf", "application/vnd.openxmlformats-officedocument.wordprocessingml.document"])

app/modules/matching_cv/models/matching_cv_logic.py

@@ -0,0 +1,60 @@
+import os
+import docx
+from dotenv import load_dotenv
+
+# import prompt template
+from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
+from langchain_core.messages import SystemMessage
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+# import the json oupput parser from the langchain core
+from langchain_core.output_parsers import JsonOutputParser
+
+# define the parser object
+parser = JsonOutputParser()
+
+# Import API key
+load_dotenv()
+
+# Define the google api key
+os.environ['GOOGLE_API_KEY'] = os.getenv('GOOGLE_API_KEY')
+GOOGLE_API_KEY = os.environ.get("GOOGLE_API_KEY")
+
+# def load cv from docx file
+def load_cv_from_docx(file):
+    doc = docx.Document(file)
+    fullText = []
+    for para in doc.paragraphs:
+        fullText.append(para.text)
+    return '\n'.join(fullText)
+
+# def matching cv and jd return percentage of matching using prompt template
+def result_matching_cv_jd(cv_text, jd_text):
+    # create the prompt template
+    chat_template = ChatPromptTemplate.from_messages(
+        [
+            SystemMessage(
+                content=(
+                    """
+                    Given the following CV and JD, calculate the percentage match between the candidate's qualifications and the job requirements:
+                    CV: {cv}
+                    JD: {jd}
+                    To determine the match percentage, analyze the skills and experience in the CV and compare them to the requirements outlined in the JD. Provide the final match percentage as a numeric value between 0-100%, along with a brief explanation of your analysis. Follow this json format: {"Skills Match": {"Required Skills": "","Candidate  Skills": "","Match Percentage": "",}, "Experience Match": {"Required Experience": "","Candidate Experience": "","Match Percentage": "",}, "Overall Match Percentage:": ""}
+                    """
+                )
+            ),
+            HumanMessagePromptTemplate.from_template(["{cv}", "{jd}"]),
+        ]
+    )
+
+    # create the chat message
+    chat_message =  chat_template.format_messages(cv=cv_text, jd=jd_text)
+
+    llm = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3, convert_system_message_to_human=True, api_key=GOOGLE_API_KEY)
+    chain = llm | parser
+    result = chain.invoke(chat_message)
+
+    return result
+
+def load_jd_from_id():
+    pass