fix: resolve MongoDB integration issues

- Fix memory record citation duplication (lines 861, 880, 933 in memory.py)
- Make vector dimensions configurable based on embedding model
- Add _get_embedding_dimensions method for proper dimension detection
- Support multiple embedding models (text-embedding-3-small, 3-large, ada-002)
- Improve citation format to use record IDs instead of duplicating text

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Mervin Praison <MervinPraison@users.noreply.github.com>

Author: github-actions[bot]

src/praisonai-agents/praisonaiagents/knowledge/knowledge.py

@@ -107,6 +107,25 @@ def _init_embedding_model(self):
         except Exception as e:
             raise Exception(f"Failed to initialize embedding model: {e}")
 
+    def _get_embedding_dimensions(self, model_name: str) -> int:
+        """Get embedding dimensions based on model name."""
+        # Common embedding model dimensions
+        model_dimensions = {
+            "text-embedding-3-small": 1536,
+            "text-embedding-3-large": 3072,
+            "text-embedding-ada-002": 1536,
+            "text-embedding-002": 1536,
+            # Add more models as needed
+        }
+        
+        # Check if model name contains known model identifiers
+        for model_key, dimensions in model_dimensions.items():
+            if model_key in model_name.lower():
+                return dimensions
+        
+        # Default to 1536 for unknown models (OpenAI standard)
+        return 1536
+    
     def _create_indexes(self):
         """Create necessary indexes for MongoDB."""
         try:
@@ -133,7 +152,7 @@ def _create_vector_index(self):
                     "fields": {
                         "embedding": {
                             "type": "knnVector",
-                            "dimensions": 1536,
+                            "dimensions": self._get_embedding_dimensions(self.embedding_model_name),
                             "similarity": "cosine"
                         }
                     }

src/praisonai-agents/praisonaiagents/memory/memory.py

@@ -144,6 +144,10 @@ def __init__(self, config: Dict[str, Any], verbose: int = 0):
 
         self._log_verbose(f"Using embedding model: {self.embedding_model}")
 
+        # Determine embedding dimensions based on model
+        self.embedding_dimensions = self._get_embedding_dimensions(self.embedding_model)
+        self._log_verbose(f"Using embedding dimensions: {self.embedding_dimensions}")
+
         # Create .praison directory if it doesn't exist
         os.makedirs(".praison", exist_ok=True)
 
@@ -351,7 +355,7 @@ def _create_vector_search_indexes(self):
                     "fields": {
                         "embedding": {
                             "type": "knnVector",
-                            "dimensions": 1536,  # OpenAI embedding dimensions
+                            "dimensions": self.embedding_dimensions,
                             "similarity": "cosine"
                         }
                     }
@@ -398,6 +402,25 @@ def _get_embedding(self, text: str) -> List[float]:
             self._log_verbose(f"Error getting embedding: {e}", logging.ERROR)
             return None
 
+    def _get_embedding_dimensions(self, model_name: str) -> int:
+        """Get embedding dimensions based on model name."""
+        # Common embedding model dimensions
+        model_dimensions = {
+            "text-embedding-3-small": 1536,
+            "text-embedding-3-large": 3072,
+            "text-embedding-ada-002": 1536,
+            "text-embedding-002": 1536,
+            # Add more models as needed
+        }
+        
+        # Check if model name contains known model identifiers
+        for model_key, dimensions in model_dimensions.items():
+            if model_key in model_name.lower():
+                return dimensions
+        
+        # Default to 1536 for unknown models (OpenAI standard)
+        return 1536
+
     # -------------------------------------------------------------------------
     #                      Basic Quality Score Computation
     # -------------------------------------------------------------------------
@@ -858,7 +881,7 @@ def search_long_term(
                             text = doc["content"]
                             # Add memory record citation
                             if "(Memory record:" not in text:
-                                text = f"{text} (Memory record: {text})"
+                                text = f"{text} (Memory record: {str(doc['_id'])})"
                             results.append({
                                 "id": str(doc["_id"]),
                                 "text": text,
@@ -877,7 +900,7 @@ def search_long_term(
                         text = doc["content"]
                         # Add memory record citation
                         if "(Memory record:" not in text:
-                            text = f"{text} (Memory record: {text})"
+                            text = f"{text} (Memory record: {str(doc['_id'])})"
                         results.append({
                             "id": str(doc["_id"]),
                             "text": text,
@@ -930,7 +953,7 @@ def search_long_term(
                         metadata = resp["metadatas"][0][i] if "metadatas" in resp else {}
                         text = resp["documents"][0][i]
                         # Add memory record citation
-                        text = f"{text} (Memory record: {text})"
+                        text = f"{text} (Memory record: {resp['ids'][0][i]})"
                         found.append({
                             "id": resp["ids"][0][i],
                             "text": text,

test_mongodb_direct.py

@@ -0,0 +1,33 @@
+#!/usr/bin/env python3
+"""Direct test of MongoDB tools"""
+import sys
+sys.path.insert(0, 'src/praisonai-agents')
+
+try:
+    # Test direct import of MongoDB tools
+    from praisonaiagents.tools.mongodb_tools import MongoDBTools
+    print('MongoDB tools import successful')
+    
+    # Test basic initialization
+    tools = MongoDBTools()
+    print('MongoDB tools initialization successful')
+    
+    # Test the _get_pymongo method which should handle missing dependency gracefully
+    pymongo = tools._get_pymongo()
+    if pymongo is None:
+        print('pymongo not available - graceful fallback working')
+    else:
+        print('pymongo available')
+    
+    # Test client connection (should fail gracefully)
+    client = tools._get_client()
+    if client is None:
+        print('MongoDB client connection failed gracefully (expected without pymongo)')
+    else:
+        print('MongoDB client connection successful')
+        
+    print('All MongoDB direct tests passed')
+except Exception as e:
+    print(f'MongoDB direct test failed: {e}')
+    import traceback
+    traceback.print_exc()

test_mongodb_integration.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+"""Test MongoDB integration"""
+import sys
+sys.path.insert(0, 'src/praisonai-agents')
+
+try:
+    from praisonaiagents.tools.mongodb_tools import MongoDBTools
+    print('MongoDB tools import successful')
+    
+    # Test basic initialization (should work even without MongoDB running)
+    tools = MongoDBTools()
+    print('MongoDB tools initialization successful')
+    
+    # Test function imports
+    from praisonaiagents.tools import mongodb_tools
+    print('MongoDB tools module import successful')
+    
+    # Test individual function imports
+    from praisonaiagents.tools import insert_document, find_documents, vector_search
+    print('Individual MongoDB function imports successful')
+    
+    print('All MongoDB integration tests passed')
+except Exception as e:
+    print(f'MongoDB integration test failed: {e}')
+    import traceback
+    traceback.print_exc()

test_mongodb_isolated.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""Isolated test of MongoDB tools"""
+import sys
+import os
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'src/praisonai-agents'))
+
+# Test if the MongoDB tools can be directly imported and used
+try:
+    # Read the mongodb_tools.py file content and check for issues
+    with open('src/praisonai-agents/praisonaiagents/tools/mongodb_tools.py', 'r') as f:
+        content = f.read()
+    
+    # Check for potential syntax or import issues
+    print("Checking MongoDB tools file...")
+    
+    # Check imports
+    if 'from importlib import util' in content:
+        print('✓ importlib import present')
+    if 'from typing import' in content:
+        print('✓ typing imports present')
+    if 'TYPE_CHECKING' in content:
+        print('✓ TYPE_CHECKING conditional imports present')
+    
+    # Check class structure
+    if 'class MongoDBTools:' in content:
+        print('✓ MongoDBTools class present')
+    if 'def _get_pymongo' in content:
+        print('✓ _get_pymongo method present')
+    if 'def _get_client' in content:
+        print('✓ _get_client method present')
+    
+    # Check MongoDB operations
+    if 'def insert_document' in content:
+        print('✓ insert_document method present')
+    if 'def vector_search' in content:
+        print('✓ vector_search method present')
+    if 'def create_vector_index' in content:
+        print('✓ create_vector_index method present')
+    
+    # Check error handling
+    if 'try:' in content and 'except' in content:
+        print('✓ Error handling present')
+    
+    # Check graceful fallback
+    if 'if util.find_spec' in content:
+        print('✓ Graceful dependency checking present')
+    
+    print('MongoDB tools file structure looks good!')
+    
+except Exception as e:
+    print(f'Error checking MongoDB tools: {e}')
+
+# Check if imports work correctly
+try:
+    # Test individual components
+    import logging
+    from typing import List, Dict, Any, Optional, Union
+    from importlib import util
+    import json
+    import time
+    from datetime import datetime
+    
+    print('✓ All required imports for MongoDB tools available')
+    
+    # Test util.find_spec functionality
+    if util.find_spec('pymongo') is None:
+        print('✓ pymongo not available - graceful fallback should work')
+    else:
+        print('✓ pymongo available')
+        
+    print('MongoDB tools dependencies check passed')
+    
+except Exception as e:
+    print(f'Error with MongoDB tools dependencies: {e}')