SimplerLLM 0.1.9__tar.gz → 0.2.0__tar.gz

{SimplerLLM-0.1.9 → SimplerLLM-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: SimplerLLM
-Version: 0.1.9
+Version: 0.2.0
 Summary: An easy-to-use Library for interacting with language models.
 Home-page: https://github.com/hassancs91/SimplerLLM
 Author: Hasan Aboul Hasan
@@ -19,25 +19,24 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 
-
 # ⚪ SimplerLLM (Beta)
 
 ⚡ Your Easy Pass to Advanced AI ⚡
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
-
 ## 🤔 What is SimplerLLM?
 
 SimplerLLM is an open-source Python library designed to simplify interactions with Large Language Models (LLMs) for researchers and beginners. It offers a unified interface for different LLM providers and a suite of tools to enhance language model capabilities and make it Super easy for anyone to develop AI-powered tools and apps.
 
 ## Easy Installation
+
 With pip:
+
 ```bash
 pip install simplerllm
 ```
 
-
 ## Features
 
 - **Unified LLM Interface**: Define an LLM instance in one line for providers like OpenAI and Google Gemini. Future versions will support more APIs and LLM providers.
@@ -45,17 +44,17 @@ pip install simplerllm
 - **RapidAPI Connector**: Connect with AI services on RapidAPI.
 - **SERP Integration**: Perform searches using DuckDuckGo, with more search engines coming soon.
 - **Prompt Template Builder**: Easily create and manage prompt templates.
-And Much More Coming Soon!
-
+  And Much More Coming Soon!
 
 ### Setting Up Environment Variables
-To use this library, you need to set several API keys in your environment. Start by creating a .env file in the root directory of your project and adding your API keys there. 
+
+To use this library, you need to set several API keys in your environment. Start by creating a .env file in the root directory of your project and adding your API keys there.
 
 🔴 This file should be kept private and not committed to version control to protect your keys.
 
 Here is an example of what your .env file should look like:
 
-``` 
+```
 OPENAI_API_KEY="your_openai_api_key_here"
 GEMENI_API_KEY="your_gemeni_api_key_here"
 CLAUDE_API_KEY="your_claude_api_key_here"
@@ -66,16 +65,13 @@ STABILITY_API_KEY="your_stability_api_key_here" #for image generation
 
 ```
 
-
-
-
 ### Creating an LLM Instance
 
 ```python
 from SimplerLLM.language.llm import LLM, LLMProvider
 
 # For OpenAI
-llm_instance = LLM.create(provider=LLMProvider.OPENAI)
+llm_instance = LLM.create(provider=LLMProvider.OPENAI, model_name="gpt-3.5-turbo")
 
 # For Google Gemini
 #llm_instance = LLM.create(provider=LLMProvider.GEMINI,model_name="gemini-pro")
@@ -83,14 +79,14 @@ llm_instance = LLM.create(provider=LLMProvider.OPENAI)
 # For Anthropic Claude 
 #llm_instance = LLM.create(LLMProvider.ANTHROPIC, model_name="claude-3-opus-20240229")
 
-
-response = llm_instance.generate_text(user_prompt="generate a 5 words sentence")
+response = llm_instance.generate_response(prompt="generate a 5 words sentence")
 
 ```
 
 ### Using Tools
 
 #### SERP
+
 ```python
 from SimplerLLM.tools.serp import search_with_serper_api
 
@@ -101,6 +97,7 @@ search_results = search_with_serper_api("your search query", num_results=3)
 ```
 
 #### Generic Text Loader
+
 ```python
 from SimplerLLM.tools.generic_loader import load_content
 
@@ -111,6 +108,7 @@ print(text_file.content)
 ```
 
 #### Calling any RapidAPI API
+
 ```python
 from  SimplerLLM.tools.rapid_api import RapidAPIClient
 
@@ -125,7 +123,6 @@ response = api_client.call_api(api_url, method='GET', params=api_params)
 
 ```
 
-
 #### Prompt Template Builder
 
 ```python
@@ -147,7 +144,7 @@ multi_value_prompt_template = """Hello {name}, your next meeting is on {date}.
 params_list = [
      {"name": "Alice", "date": "January 10th", "object" : "dog"},
      {"name": "Bob", "date": "January 12th", "object" : "bag"},
-     {"name": "Charlie", "date": "January 15th", "object" : "pen"} 
+     {"name": "Charlie", "date": "January 15th", "object" : "pen"}
 ]
 
 
@@ -158,17 +155,20 @@ print(generated_prompts[0])
 
 ```
 
-
 ## Chunking Functions
+
 We have introduced new functions to help you split texts into manageable chunks based on different criteria. These functions are part of the chunker tool.
 
 ### chunk_by_max_chunk_size
+
 This function splits text into chunks with a maximum size, optionally preserving sentence structure.
 
 ### chunk_by_sentences
+
 This function splits the text into chunks based on sentences.
 
 ### chunk_by_paragraphs
+
 This function splits text into chunks based on paragraphs.
 
 Example
@@ -187,8 +187,8 @@ chunks = chunker.chunk_by_max_chunk_size(text, 100, True)
 
 ```
 
-
 ### Next Updates
+
 - Adding More Tools
 - Interacting With Local LLMs
 - Prompt Optimization
@@ -196,4 +196,4 @@ chunks = chunker.chunk_by_max_chunk_size(text, 100, True)
 - GPT Trainer
 - Document Chunker
 - Advanced Document Loader
-- Integration With More Providers 
+- Integration With More Providers

SimplerLLM-0.2.0/SimplerLLM/language/embeddings.py

@@ -0,0 +1,251 @@
+# import SimplerLLM.language.llm_providers.openai_llm as openai_llm
+# import SimplerLLM.language.llm_providers.gemini_llm as gemini_llm
+# import SimplerLLM.language.llm_providers.anthropic_llm as anthropic_llm
+# from enum import Enum
+
+
+# class EmbeddingsProvider(Enum):
+#     OPENAI = 1
+#     GEMINI = 2
+#     ANTHROPIC = 3
+
+
+# class LLM:
+#     def __init__(
+#         self, provider=EmbeddingsProvider.OPENAI, model_name="text-embedding-3-small"
+#     ):
+#         self.provider = provider
+#         self.model_name = model_name
+
+#     @staticmethod
+#     def create(
+#         provider=None,
+#         model_name=None,
+#     ):
+#         if provider == EmbeddingsProvider.OPENAI:
+#             return OpenAILLM(provider, model_name)
+#         if provider == EmbeddingsProvider.GEMINI:
+#             return GeminiLLM(provider, model_name)
+#         if provider == EmbeddingsProvider.ANTHROPIC:
+#             return AnthropicLLM(provider, model_name)
+#         else:
+#             return None
+
+#     def set_model(self, provider):
+#         if not isinstance(provider, EmbeddingsProvider):
+#             raise ValueError("Provider must be an instance of EmbeddingsProvider Enum")
+#         self.provider = provider
+
+
+# class OpenAILLM(LLM):
+#     def __init__(self, model, model_name):
+#         super().__init__(model, model_name)
+
+#     def generate_embeddings(
+#         self,
+#         user_input,
+#         model_name=None,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return openai_llm.generate_text(
+#             user_input=user_input,
+#             model_name=model_name,
+#         )
+
+
+# class GeminiLLM(LLM):
+#     def __init__(self, model, model_name, temperature, top_p):
+#         super().__init__(model, model_name, temperature, top_p)
+
+#     def generate_text(
+#         self,
+#         user_prompt,
+#         system_prompt=None,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return gemini_llm.generate_text(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     def generate_full_response(
+#         self,
+#         user_prompt,
+#         system_prompt,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return gemini_llm.generate_full_response(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     async def generate_text_async(
+#         self,
+#         user_prompt,
+#         system_prompt=None,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return await gemini_llm.generate_text_async(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     async def generate_full_response_async(
+#         self,
+#         user_prompt,
+#         system_prompt,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return await gemini_llm.generate_full_response_async(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+
+# class AnthropicLLM(LLM):
+#     def __init__(self, model, model_name, temperature, top_p):
+#         super().__init__(model, model_name, temperature, top_p)
+
+#     def generate_text(
+#         self,
+#         user_prompt,
+#         system_prompt=None,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return anthropic_llm.generate_text(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     def generate_full_response(
+#         self,
+#         user_prompt,
+#         system_prompt,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return anthropic_llm.generate_full_response(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     async def generate_text_async(
+#         self,
+#         user_prompt,
+#         system_prompt=None,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return await anthropic_llm.generate_text_async(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )
+
+#     async def generate_full_response_async(
+#         self,
+#         user_prompt,
+#         system_prompt,
+#         model_name=None,
+#         temperature=None,
+#         top_p=None,
+#         max_tokens=2024,
+#     ):
+#         # Use instance values as defaults if not provided
+#         model_name = model_name if model_name is not None else self.model_name
+#         temperature = temperature if temperature is not None else self.temperature
+#         top_p = top_p if top_p is not None else self.top_p
+
+#         return await anthropic_llm.generate_full_response_async(
+#             user_prompt=user_prompt,
+#             system_prompt=system_prompt,
+#             model_name=model_name,
+#             temperature=temperature,
+#             top_p=top_p,
+#             max_tokens=max_tokens,
+#         )

SimplerLLM-0.2.0/SimplerLLM/language/llm.py

@@ -0,0 +1,206 @@
+import SimplerLLM.language.llm_providers.openai_llm as openai_llm
+import SimplerLLM.language.llm_providers.gemini_llm as gemini_llm
+import SimplerLLM.language.llm_providers.anthropic_llm as anthropic_llm
+from enum import Enum
+
+
+class LLMProvider(Enum):
+    OPENAI = 1
+    GEMINI = 2
+    ANTHROPIC = 3
+
+
+class LLM:
+    def __init__(
+        self,
+        provider=LLMProvider.OPENAI,
+        model_name="gpt-3.5-turbo",
+        temperature=0.7,
+        top_p=1.0,
+    ):
+        self.provider = provider
+        self.model_name = model_name
+        self.temperature = temperature
+        self.top_p = top_p
+
+    @staticmethod
+    def create(
+        provider=None,
+        model_name=None,
+        temperature=0.7,
+        top_p=1.0,
+    ):
+        if provider == LLMProvider.OPENAI:
+            return OpenAILLM(provider, model_name, temperature, top_p)
+        if provider == LLMProvider.GEMINI:
+            return GeminiLLM(provider, model_name, temperature, top_p)
+        if provider == LLMProvider.ANTHROPIC:
+            return AnthropicLLM(provider, model_name, temperature, top_p)
+        else:
+            return None
+
+    def set_model(self, provider):
+        if not isinstance(provider, LLMProvider):
+            raise ValueError("Provider must be an instance of LLMProvider Enum")
+        self.provider = provider
+
+    def prepare_params(self, model_name, temperature, top_p):
+        # Use instance values as defaults if parameters are not provided
+        return {
+            "model_name": model_name if model_name else self.model_name,
+            "temperature": temperature if temperature else self.temperature,
+            "top_p": top_p if top_p else self.top_p,
+        }
+
+
+class OpenAILLM(LLM):
+    def __init__(self, model, model_name, temperature, top_p):
+        super().__init__(model, model_name, temperature, top_p)
+
+    def generate_response(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return openai_llm.generate_response(**params)
+
+    async def generate_response_async(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return await openai_llm.generate_response_async(**params)
+
+
+class GeminiLLM(LLM):
+    def __init__(self, model, model_name, temperature, top_p):
+        super().__init__(model, model_name, temperature, top_p)
+
+    def generate_response(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return gemini_llm.generate_response(**params)
+
+    async def generate_response_async(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return await gemini_llm.generate_response_async(**params)
+
+
+class AnthropicLLM(LLM):
+    def __init__(self, model, model_name, temperature, top_p):
+        super().__init__(model, model_name, temperature, top_p)
+
+    def generate_response(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return anthropic_llm.generate_response(**params)
+
+    async def generate_response_async(
+        self,
+        model_name=None,
+        prompt=None,
+        messages=None,
+        system_prompt="You are a helpful AI Assistant",
+        temperature=0.7,
+        max_tokens=300,
+        top_p=1.0,
+        full_response=False,
+    ):
+        params = self.prepare_params(model_name, temperature, top_p)
+        params.update(
+            {
+                "prompt": prompt,
+                "messages": messages,
+                "system_prompt": system_prompt,
+                "max_tokens": max_tokens,
+                "full_response": full_response,
+            }
+        )
+        return await anthropic_llm.generate_response_async(**params)