feat(hr-goal-alignment): sync all updated files

ai/generative-ai-service/hr-goal-alignment/.gitignore

@@ -1,8 +1,8 @@
 **/__pycache__/
 venv/
-files/venv/
-**/config.py
+config.py
 .DS_Store
 data/
 *.log
 *.txt
+!requirements.txt

ai/generative-ai-service/hr-goal-alignment/README.md

@@ -28,8 +28,9 @@ See [LICENSE](./LICENSE) for more details.
 
 ---
 
+> ORACLE AND ITS AFFILIATES DO NOT PROVIDE ANY WARRANTY WHATSOEVER, EXPRESS OR IMPLIED, FOR ANY SOFTWARE, MATERIAL OR CONTENT OF ANY KIND CONTAINED OR PRODUCED WITHIN THIS REPOSITORY, AND IN PARTICULAR SPECIFICALLY DISCLAIM ANY AND ALL IMPLIED WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. FURTHERMORE, ORACLE AND ITS AFFILIATES DO NOT REPRESENT THAT ANY CUSTOMARY SECURITY REVIEW HAS BEEN PERFORMED WITH RESPECT TO ANY SOFTWARE, MATERIAL OR CONTENT CONTAINED OR PRODUCED WITHIN THIS REPOSITORY. IN ADDITION, AND WITHOUT LIMITING THE FOREGOING, THIRD PARTIES MAY HAVE POSTED SOFTWARE, MATERIAL OR CONTENT TO THIS REPOSITORY WITHOUT ANY REVIEW. USE AT YOUR OWN RISK.
 
 
 ## Disclaimer
 
-ORACLE AND ITS AFFILIATES DO NOT PROVIDE ANY WARRANTY WHATSOEVER, EXPRESS OR IMPLIED, FOR ANY SOFTWARE, MATERIAL OR CONTENT OF ANY KIND CONTAINED OR PRODUCED WITHIN THIS REPOSITORY, AND IN PARTICULAR SPECIFICALLY DISCLAIM ANY AND ALL IMPLIED WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE.  FURTHERMORE, ORACLE AND ITS AFFILIATES DO NOT REPRESENT THAT ANY CUSTOMARY SECURITY REVIEW HAS BEEN PERFORMED WITH RESPECT TO ANY SOFTWARE, MATERIAL OR CONTENT CONTAINED OR PRODUCED WITHIN THIS REPOSITORY. IN ADDITION, AND WITHOUT LIMITING THE FOREGOING, THIRD PARTIES MAY HAVE POSTED SOFTWARE, MATERIAL OR CONTENT TO THIS REPOSITORY WITHOUT ANY REVIEW. USE AT YOUR OWN RISK.
+ORACLE AND ITS AFFILIATES DO NOT PROVIDE ANY WARRANTY WHATSOEVER, EXPRESS OR IMPLIED, FOR ANY SOFTWARE, MATERIAL OR CONTENT OF ANY KIND CONTAINED OR PRODUCED WITHIN THIS REPOSITORY, AND IN PARTICULAR SPECIFICALLY DISCLAIM ANY AND ALL IMPLIED WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, AND FITNESS FOR A PARTICULAR PURPOSE. FURTHERMORE, ORACLE AND ITS AFFILIATES DO NOT REPRESENT THAT ANY CUSTOMARY SECURITY REVIEW HAS BEEN PERFORMED WITH RESPECT TO ANY SOFTWARE, MATERIAL OR CONTENT CONTAINED OR PRODUCED WITHIN THIS REPOSITORY. IN ADDITION, AND WITHOUT LIMITING THE FOREGOING, THIRD PARTIES MAY HAVE POSTED SOFTWARE, MATERIAL OR CONTENT TO THIS REPOSITORY WITHOUT ANY REVIEW. USE AT YOUR OWN RISK.

ai/generative-ai-service/hr-goal-alignment/files/Org_Chart.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 import streamlit as st
 from urllib.parse import quote, unquote
 
@@ -100,7 +99,7 @@ def create_org_chart():
 """
 
 # Display the chart with HTML component
-st.components.v1.html(html_chart, height=520, scrolling=True) # type: ignore
+st.components.v1.html(html_chart, height=520, scrolling=True)
 
 # Show details section for selected employee
 # ------------------------------------------------------------
@@ -182,5 +181,5 @@ def chip_style(val):
                 else "background-color:#f8d7da;font-weight:bold"
             )
 
-        styled = goals_pretty.style.applymap(chip_style, subset=[LABEL_COL]) # type: ignore
+        styled = goals_pretty.style.applymap(chip_style, subset=[LABEL_COL])
         st.dataframe(styled, use_container_width=True, hide_index=True)

ai/generative-ai-service/hr-goal-alignment/files/README.md

@@ -51,6 +51,7 @@ The system integrates with Oracle Database and uses OCI's Generative AI models t
 ├── utils.py
 ├── requirements.txt
 └── README.md
+```
 
 ## Setup Instructions
 

ai/generative-ai-service/hr-goal-alignment/files/app.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 import streamlit as st
 from pathlib import Path
 
@@ -30,4 +29,4 @@
 
 
 pg = st.navigation(pages)
-pg.run()
+pg.run()

ai/generative-ai-service/hr-goal-alignment/files/config_template.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 # config_template.py
 
 # === OCI Configuration ===

ai/generative-ai-service/hr-goal-alignment/files/course_vector_utils.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 from typing import List, Dict, Optional
 from langchain_community.vectorstores import OracleVS
 import os
@@ -13,7 +12,6 @@
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import OCIGenAIEmbeddings
 from langchain_core.documents import Document
-from langchain_community.vectorstores.utils import DistanceStrategy
 
 # Use the project's config file
 import config
@@ -62,7 +60,7 @@ def _initialize_vector_store(self) -> OracleVS:
             client=self.db_conn, # Use the connection passed in __init__
             embedding_function=self.embeddings, # Use the embeddings initialized in __init__
             table_name=config.VECTOR_TABLE_NAME, # Use table name from project config
-            distance_strategy=DistanceStrategy.COSINE
+            distance_strategy="COSINE"
         )
 
     # LLM initialization removed.
@@ -169,3 +167,5 @@ def similarity_search(self, query: str, k: int = 5) -> List[Document]:
         except Exception as e:
             logger.error(f"Error during similarity search: {e}", exc_info=True)
             return []
+
+

ai/generative-ai-service/hr-goal-alignment/files/data_ingestion_courses.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 import logging
 import sys
 import oracledb

ai/generative-ai-service/hr-goal-alignment/files/gen_ai_service/inference.py

@@ -1,4 +1,3 @@
-# Copyright (c) 2025 Oracle and/or its affiliates.
 import json
 import logging
 import sys
@@ -53,7 +52,8 @@ def recommend_courses(profile, feedback) -> dict:
     model = get_llm_model()
     response = {}
     try:
-        response = model.with_structured_output(schema).invoke(
+        # Get raw output first for debugging
+        raw_output = model.invoke(
             [
                 SystemMessage(content=prompt_sys),
                 HumanMessage(
@@ -63,10 +63,27 @@ def recommend_courses(profile, feedback) -> dict:
                 ),
             ]
         )
+        logger.info(f"Raw LLM response before parsing:\n{raw_output}")
+        # Now parse the structured output
+        result = model.with_structured_output(schema).invoke(
+            [
+                SystemMessage(content=prompt_sys),
+                HumanMessage(
+                    content=prompt_user.format(
+                        EMPLOYEE_PROFILE=profile, MANAGER_FEEDBACK=feedback
+                    )
+                ),
+            ]
+        )
+        if result is None:
+            logger.warning("GenAI model response couldn't be parsed into the expected schema.")
+            logger.warning("Consider inspecting the raw output.")
+        else:
+            response = dict(result) if not isinstance(result, dict) else result
     except Exception as e:
         logger.error(f"Error during recommended_courses execution: {e}")
-
-    return response # type: ignore
+    logger.info(f"Returning response from recommend_courses: {response}")
+    return response
 
 
 
@@ -82,7 +99,7 @@ def classify_smart_goal(goal_description) -> dict:
     except Exception as e:
         logger.error(f"Error during recommended_courses execution: {e}")
 
-    return json.loads(response.content) # type: ignore
+    return json.loads(response.content)
 
 
 prompt_sys = """
@@ -133,6 +150,58 @@ def classify_smart_goal(goal_description) -> dict:
 DO NOT wrap your response in code blocks, backticks, or any other formatting. Return ONLY the raw JSON object itself.
 """
 
+
+new_prompt_user = """
+Based on the following information about an employee and their performance, recommend appropriate training courses.
+
+**Employee Profile:**
+{EMPLOYEE_PROFILE}
+
+**Manager Feedback:**
+{MANAGER_FEEDBACK}
+
+Your task:
+
+1. Identify exactly 3 skill-based focus areas for this employee to develop, prioritized according to:
+   - The most critical issues raised in the manager's feedback
+   - Then their job title and core responsibilities
+   - Then existing skills and experience level
+
+2. For each focus area, recommend exactly 2 course titles that:
+   - Explicitly include difficulty level in the title using: "(Beginner)", "(Intermediate)", or "(Advanced)"
+   - Address the skill gap clearly
+   - Are appropriate for the employee's experience
+
+**Output Format:**
+
+Return ONLY a JSON object with a single key: `"recommended_courses"`  
+- This key must map to an object
+- Each key in that object is a focus area (string)
+- Each value is a list of exactly two course titles (strings)
+
+**Example:**
+{
+  "recommended_courses": {
+    "Strategic Communication": [
+      "Influential Communication for Technical Professionals (Intermediate)",
+      "Executive Presence and Presentation Skills (Advanced)"
+    ],
+    "Technical Leadership": [
+      "Leading High-Performance Technical Teams (Intermediate)",
+      "Strategic Technical Decision Making (Advanced)"
+    ],
+    "Project Estimation": [
+      "Fundamentals of Project Estimation (Beginner)",
+      "Advanced Techniques in Project Scoping and Estimation (Intermediate)"
+    ]
+  }
+}
+
+⚠️ Do NOT include any explanations, markdown formatting, backticks, or extra text. Only return the raw JSON object as shown.
+"""
+
+
+
 prompt_user = """
 Based on the following information about an employee and their performance, recommend appropriate training courses: