Phase2/HuyDN: edit Dockerfile

.gitignore

@@ -5,3 +5,4 @@ credentials/
 data/CV
 data/JD
 data/QUESTION
+!.gitkeep

app/modules/crud_cvs/models/crud_cvs.py

@@ -16,6 +16,12 @@ def remove_file_cvs(file_url):
     blob.delete()
     return True
 
+def download_file_cvs(file_url):
+    # download file from firebase storage using "gs://" link
+    blob = firebase_bucket.blob(file_url.split(f"gs://{firebase_bucket.name}/")[1])
+    # download file and return string in file
+    return blob.download_as_text()
+
 def get_all_cvs():
     # Get all documents from the collection
     docs = firebase_db.collection("cvs").stream()

app/modules/crud_jds/models/crud_jds.py

@@ -17,6 +17,12 @@ def remove_file_jds(file_url):
     blob.delete()
     return True
 
+def download_file_jds(file_url):
+    # download file from firebase storage using "gs://" link
+    blob = firebase_bucket.blob(file_url.split(f"gs://{firebase_bucket.name}/")[1])
+    # download file and return string in file
+    return blob.download_as_text()
+
 def get_all_jds():
     # Get all documents from the collection
     docs = firebase_db.collection("jds").stream()

app/modules/matching_cv/__init__.py

@@ -3,7 +3,7 @@ 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
+from app.modules.matching_cv.models.matching_cv_logic import result_matching_cv_jd
 
 cvmatching_router = APIRouter(prefix="/cvmatching", tags=["cvmatching"])
 
@@ -13,24 +13,23 @@ async def index():
 
 @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):
+async def matching_cv_jd(id_jd: str, id_cv:str):
     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"}
+        pass
+        # # 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/matching_cv_logic.py

@@ -47,6 +47,3 @@ def result_matching_cv_jd(cv_text, jd_text):
     result = chain.invoke(chat_message)
 
     return result
-
-def load_jd_from_id():
-    pass

app/modules/question_tests_retrieval/__init__.py

@@ -2,8 +2,8 @@ from fastapi import APIRouter, UploadFile, File
 from typing import Annotated
 
 from app.modules.question_tests_retrieval.models.jd2text import jobdes2text
-# from app.modules.question_tests_retrieval.models.text2vector import text2vector
 from app.modules.question_tests_retrieval.models.question_tests_logic import get_question_tests
+from app.modules.crud_jds.models.crud_jds import get_jd_by_id, download_file_jds
 
 qtretrieval_router = APIRouter(prefix="/qtretrieval", tags=["qtretrieval"])
 
@@ -11,18 +11,19 @@ qtretrieval_router = APIRouter(prefix="/qtretrieval", tags=["qtretrieval"])
 async def index():
     return {"message": "Welcome to question retrieval page"}
 
-@qtretrieval_router.post("/send_jd")
+@qtretrieval_router.post("/send_jd_to_get_question")
 # only upload .txt file
-async def send_jd(txt_file: Annotated[UploadFile, File(..., description="The JD file (only .txt file)", media_type=["text/plain"])]):
+async def send_jd_to_get_question(id_jd: str):
     try:
-        # read the txt file with format
-        jobdes = txt_file.file.read().decode("utf-8")
-        sumaryjd_text = jobdes2text(jobdes)
+        jd_document = get_jd_by_id(id_jd)
+        # download jd file from firebase storage
+        jd_file_string = download_file_jds(jd_document["jd_url"])
+        sumaryjd_text = jobdes2text(jd_file_string)
         if get_question_tests(sumaryjd_text):
             return {"message": "Send JD successfully and get question test successfully",
                     "sumaryjd_text": sumaryjd_text}
         else:
             return {"message": "Please upload only .txt file", "error": str(e)}
     except Exception as e:
-        return {"message": "Please upload only .txt file", "error": str(e)}
+        return {"message": "Have error when find JD in database", "error": str(e)}