modified all tools with crew ai BaseModel

agents/tools/knowledge_tools.py

@@ -1,15 +1,16 @@
-from .base_tool import BaseTool
+# .base_tool import BaseTool
 from utils.knowledge_base import KnowledgeBase
-from pydantic import BaseModel, PrivateAttr
+#from pydantic import BaseModel, PrivateAttr
+from crewai_tools import BaseTool
 
 class SearchKnowledgeTool(BaseTool):
     name: str = "search_knowledge"
     description: str = "Search self-help or spiritual wisdom."
-    _kp: KnowledgeBase = PrivateAttr()
+    #_kp: KnowledgeBase = PrivateAttr()
     def __init__(self, config=None):
         super().__init__()
-        self._kb = KnowledgeBase(config)
-    def __call__(self, query: str, k: int = 5):
+        self.kb = KnowledgeBase(config)
+    def _run(self, query: str, k: int = 5):
         return self.kb.search(query, k=k) if self.kb.is_initialized() else \
             [{"text": "General wisdom", "score": 1.0}]
 
@@ -18,7 +19,7 @@ class ExtractWisdomTool(BaseTool):
     description: str = "Extract most relevant wisdom for a given query."
     def __init__(self, config=None):
         super().__init__()
-    def __call__(self, search_results: list, user_context: dict):
+    def _run(self, search_results: list, user_context: dict):
         return search_results[:3]
 
 class SuggestPracticesTool(BaseTool):
@@ -26,7 +27,7 @@ class SuggestPracticesTool(BaseTool):
     description: str = "Recommend meditations or self-care practices."
     def __init__(self, config=None):
         super().__init__()
-    def __call__(self, emotional_state: str, cultural_context: str = None):
+    def _run(self, emotional_state: str, cultural_context: str = None):
         return {"name": "Mindful Breathing", "description": "Focus on your breath to calm the mind."}
 
 class KnowledgeTools:

agents/tools/llm_tools.py

@@ -1,37 +1,38 @@
-from .base_tool import BaseTool
+#from .base_tool import BaseTool
 from models.tinygpt2_model import TinyGPT2Model
-from pydantic import BaseModel, PrivateAttr
+#from pydantic import BaseModel, PrivateAttr
+from crewai_tools import BaseTool
 
 class MistralChatTool(BaseTool):
     name: str = "mistral_chat"
     description: str = "Generate an empathetic AI chat response."
-    _model: TinyGPT2Model = PrivateAttr()
+    #_model: TinyGPT2Model = PrivateAttr()
     def __init__(self, config=None):
         super().__init__()
-        self._model = TinyGPT2Model()
-    def __call__(self, prompt: str, context: dict = None):
+        self.model = TinyGPT2Model()
+    def _run(self, prompt: str, context: dict = None):
         msg = f"Context: {context}\nUser: {prompt}" if context else prompt
         return self.model.generate(msg)
 
 class GenerateAdviceTool(BaseTool):
     name: str = "generate_advice"
     description: str = "Generate personalized advice."
-    _model: TinyGPT2Model = PrivateAttr()
+    #_model: TinyGPT2Model = PrivateAttr()
     def __init__(self, config=None):
         super().__init__()
-        self._model = TinyGPT2Model()
-    def __call__(self, user_analysis: dict, wisdom_quotes: list):
+        self.model = TinyGPT2Model()
+    def _run(self, user_analysis: dict, wisdom_quotes: list):
         prompt = f"Advice for: {user_analysis}, with wisdom: {wisdom_quotes}"
         return self.model.generate(prompt, max_length=300)
 
 class SummarizeConversationTool(BaseTool):
     name: str = "summarize_conversation"
     description: str = "Summarize chat with insights and next steps."
-    _model: TinyGPT2Model = PrivateAttr()
+    #_model: TinyGPT2Model = PrivateAttr()
     def __init__(self, config=None):
         super().__init__()
-        self._model = TinyGPT2Model()
-    def __call__(self, conversation: list):
+        self.model = TinyGPT2Model()
+    def _run(self, conversation: list):
         prompt = f"Summarize: {conversation}"
         return self.model.generate(prompt, max_length=200)
 

agents/tools/validation_tools.py

@@ -397,17 +397,18 @@ class ValidationResult:
         
 #         return resources.get(location.lower(), resources["global"])
 
-from .base_tool import BaseTool
+#from .base_tool import BaseTool
+from crewai_tools import BaseTool
 
 class ValidateResponseTool(BaseTool):
     name: str = "validate_response"
     description: str = "Validates safety and helpfulness."
-    _config: object = PrivateAttr()
+    #_config: object = PrivateAttr()
     def __init__(self, config=None, **data):
         super().__init__(**data)
-        self._config = config
+        self.config = config
         # ... any required initialization ...
-    def __call__(self, response: str, context: dict = None):
+    def _run(self, response: str, context: dict = None):
         # Place your actual validation logic here, include dummy for illustration
         # For full validation logic, use your own code! 
         #     """Result of validation check"""

agents/tools/voice_tools.py

@@ -1,13 +1,14 @@
 import numpy as np
 import asyncio
-from .base_tool import BaseTool
+#from .base_tool import BaseTool
 from models.tinygpt2_model import TinyGPT2Model
 from transformers import pipeline, AutoProcessor, AutoModelForSpeechSeq2Seq
 import os
 import tempfile
 import soundfile as sf
 import torch
-from pydantic import BaseModel, PrivateAttr
+#from pydantic import BaseModel, PrivateAttr
+from crewai_tools import BaseTool
 class MultilingualVoiceProcessor:
     
     def __init__(self, model_name="openai/whisper-base", device=None):
@@ -42,11 +43,11 @@ class MultilingualVoiceProcessor:
 class TranscribeAudioTool(BaseTool):
     name: str = "transcribe_audio"
     description: str = "Transcribe audio to text and detect language."
-    _vp: MultilingualVoiceProcessor = PrivateAttr()
+    #_vp: MultilingualVoiceProcessor = PrivateAttr()
     def __init__(self, config=None):
         super().__init__()
-        self._vp = MultilingualVoiceProcessor()
-    def __call__(self, audio_data: np.ndarray, language=None):
+        self.vp = MultilingualVoiceProcessor()
+    def _run(self, audio_data: np.ndarray, language=None):
         text, detected_lang = asyncio.run(self.vp.transcribe(audio_data, language))
         return {"text": text, "language": detected_lang}
 
@@ -55,7 +56,7 @@ class DetectEmotionTool(BaseTool):
     description: str = "Detect the emotional state from text."
     def __init__(self, config=None):
         super().__init__()
-    def __call__(self, text: str):
+    def _run(self, text: str):
         model = TinyGPT2Model()
         prompt = f'Analyse emotions in: "{text}". Format: JSON with primary_emotion, intensity, feelings, concerns.'
         response = model.generate(prompt)
@@ -69,7 +70,7 @@ class GenerateReflectiveQuestionsTool(BaseTool):
     description: str = "Generate reflective questions."
     def __init__(self, config=None):
         super().__init__()
-    def __call__(self, context: dict):
+    def _run(self, context: dict):
         emotion = context.get("primary_emotion", "neutral")
         questions_map = {
             "anxiety": ["What triggers your anxiety?", "How do you cope?"],