mb-rag 1.1.6__tar.gz → 1.1.7__tar.gz

{mb_rag-1.1.6 → mb_rag-1.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mb_rag
-Version: 1.1.6
+Version: 1.1.7
 Summary: RAG function file
 Author: ['Malav Bateriwala']
 Requires-Python: >=3.8

{mb_rag-1.1.6 → mb_rag-1.1.7}/README.md

@@ -9,6 +9,7 @@ MB-RAG is a flexible Python package that provides modular building blocks for cr
   - Anthropic (Claude)
   - Google (Gemini)
   - Ollama (Local models)
+  - Groq
 
 - **RAG Capabilities**:
   - Text splitting and chunking

{mb_rag-1.1.6 → mb_rag-1.1.7}/mb_rag/chatbot/basic.py

@@ -54,7 +54,7 @@ class ModelFactory:
         """
         Factory method to create any type of model
         Args:
-            model_type (str): Type of model to create. Default is OpenAI. Options are openai, anthropic, google, ollama
+            model_type (str): Type of model to create. Default is OpenAI. Options are openai, anthropic, google, ollama , groq
             model_name (str): Name of the model
             **kwargs: Additional arguments
         Returns:
@@ -64,7 +64,8 @@ class ModelFactory:
             'openai': self.create_openai,
             'anthropic': self.create_anthropic,
             'google': self.create_google,
-            'ollama': self.create_ollama
+            'ollama': self.create_ollama,
+            'groq': self.create_groq
         }
         
         model_data = creators.get(model_type)
@@ -144,6 +145,23 @@ class ModelFactory:
         kwargs["model"] = model_name
         return Ollama(**kwargs)
 
+    @classmethod
+    def create_groq(cls, model_name: str = "llama-3.3-70b-versatile", **kwargs) -> Any:
+        """
+        Create Groq chatbot model
+        Args:
+            model_name (str): Name of the model
+            **kwargs: Additional arguments. Options are: temperature, groq_api_key, model_name
+        Returns:
+            ChatGroq: Chatbot model
+        """
+        if not check_package("langchain-groq"):
+            raise ImportError("Langchain Groq package not found. Please install it using: pip install langchain-groq")
+
+        from langchain_groq import ChatGroq
+        kwargs["model"] = model_name
+        return ChatGroq(**kwargs)
+
     def invoke_query(self,query: str,get_content_only: bool = True,images: list = None,pydantic_model = None) -> str:
         """
         Invoke the model

{mb_rag-1.1.6 → mb_rag-1.1.7}/mb_rag/version.py

@@ -1,5 +1,5 @@
 MAJOR_VERSION = 1
 MINOR_VERSION = 1
-PATCH_VERSION = 6
+PATCH_VERSION = 7
 version = '{}.{}.{}'.format(MAJOR_VERSION, MINOR_VERSION, PATCH_VERSION)
 __all__  = ['MAJOR_VERSION', 'MINOR_VERSION', 'PATCH_VERSION', 'version']

{mb_rag-1.1.6 → mb_rag-1.1.7}/mb_rag.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mb_rag
-Version: 1.1.6
+Version: 1.1.7
 Summary: RAG function file
 Author: ['Malav Bateriwala']
 Requires-Python: >=3.8