vectara-agentic 0.1.1__tar.gz → 0.1.2__tar.gz

{vectara_agentic-0.1.1/vectara_agentic.egg-info → vectara_agentic-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectara_agentic
-Version: 0.1.1
+Version: 0.1.2
 Summary: A Python package for creating AI Assistants and AI Agents with Vectara
 Home-page: https://github.com/vectara/py-vectara-agentic
 Author: Ofer Mendelevitch
@@ -31,6 +31,7 @@ Requires-Dist: mypy==1.11.0
 Requires-Dist: pylint==3.2.6
 Requires-Dist: flake8==7.1.0
 Requires-Dist: pymongo==4.6.1
+Requires-Dist: python-dotenv==1.0.1
 
 # vectara-agentic
 
@@ -138,15 +139,12 @@ mult_tool = ToolsFactory().create_tool(mult_func)
 
 ```python
 agent = Agent(
-    agent_type = agent_type,
     tools = tools,
     topic = topic_of_expertise
     custom_instructions = financial_bot_instructions,
     update_func = update_func
 )
 ```
-
-- `agent_type` is one of `AgentType.REACT` or `AgentTypeOpenAI`
 - `tools` is the list of tools you want to provide to the agent
 - `topic` is a string that defines the expertise you want the agent to specialize in.
 - `custom_instructions` is an optional string that defines special instructions to the agent
@@ -154,6 +152,8 @@ agent = Agent(
   The inputs to this function you provide are `status_type` of type AgentStatusType and 
   `msg` which is a string.
 
+Note that the Agent type (`OPENAI` or `REACT`) is defined as an environment variables `VECTARA_AGENTIC_AGENT_TYPE`.
+
 For example, for a financial agent we can use:
 
 ```python

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/README.md

@@ -104,15 +104,12 @@ mult_tool = ToolsFactory().create_tool(mult_func)
 
 ```python
 agent = Agent(
-    agent_type = agent_type,
     tools = tools,
     topic = topic_of_expertise
     custom_instructions = financial_bot_instructions,
     update_func = update_func
 )
 ```
-
-- `agent_type` is one of `AgentType.REACT` or `AgentTypeOpenAI`
 - `tools` is the list of tools you want to provide to the agent
 - `topic` is a string that defines the expertise you want the agent to specialize in.
 - `custom_instructions` is an optional string that defines special instructions to the agent
@@ -120,6 +117,8 @@ agent = Agent(
   The inputs to this function you provide are `status_type` of type AgentStatusType and 
   `msg` which is a string.
 
+Note that the Agent type (`OPENAI` or `REACT`) is defined as an environment variables `VECTARA_AGENTIC_AGENT_TYPE`.
+
 For example, for a financial agent we can use:
 
 ```python

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/requirements.txt

@@ -18,3 +18,4 @@ mypy==1.11.0
 pylint==3.2.6
 flake8==7.1.0
 pymongo==4.6.1
+python-dotenv==1.0.1

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/setup.py

@@ -8,7 +8,7 @@ def read_requirements():
 
 setup(
     name="vectara_agentic",
-    version="0.1.1",
+    version="0.1.2",
     author="Ofer Mendelevitch",
     author_email="ofer@vectara.com",
     description="A Python package for creating AI Assistants and AI Agents with Vectara",

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/vectara_agentic/_callback.py

@@ -11,13 +11,15 @@ from .types import AgentStatusType
 
 
 class AgentCallbackHandler(BaseCallbackHandler):
-    """Callback handler to track agent status
+    """
+    Callback handler to track agent status
 
     This handler simply keeps track of event starts/ends, separated by event types.
     You can use this callback handler to keep track of agent progress.
 
     Args:
-    - fn: callable function agent will call back to report on agent progress
+    
+        fn: callable function agent will call back to report on agent progress
     """
 
     def __init__(self, fn: Callable = None) -> None:

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/vectara_agentic/agent.py

@@ -26,9 +26,11 @@ load_dotenv(override=True)
 
 
 def get_prompt(prompt_template: str, topic: str, custom_instructions: str):
-    """Generate a prompt by replacing placeholders with topic and date.
+    """
+    Generate a prompt by replacing placeholders with topic and date.
 
     Args:
+
         prompt_template (str): The template for the prompt.
         topic (str): The topic to be included in the prompt.
 
@@ -50,7 +52,9 @@ def retry_if_exception(exception):
 
 
 class Agent:
-    """Agent class for handling different types of agents and their interactions."""
+    """
+    Agent class for handling different types of agents and their interactions.
+    """
 
     def __init__(
         self,
@@ -59,13 +63,15 @@ class Agent:
         custom_instructions: str = "",
         update_func: Optional[Callable[[AgentStatusType, str], None]] = None,
     ):
-        """Initialize the agent with the specified type, tools, topic, and system message.
+        """
+        Initialize the agent with the specified type, tools, topic, and system message.
 
         Args:
-        - tools (list[FunctionTool]): A list of tools to be used by the agent.
-        - topic (str, optional): The topic for the agent. Defaults to 'general'.
-        - custom_instructions (str, optional): custom instructions for the agent. Defaults to ''.
-        - update_func (Callable): a callback function the code calls on any agent updates
+
+            tools (list[FunctionTool]): A list of tools to be used by the agent.
+            topic (str, optional): The topic for the agent. Defaults to 'general'.
+            custom_instructions (str, optional): custom instructions for the agent. Defaults to ''.
+            update_func (Callable): a callback function the code calls on any agent updates.
         """
         self.agent_type = AgentType(os.getenv("VECTARA_AGENTIC_AGENT_TYPE", "OPENAI"))
         self.tools = tools
@@ -110,21 +116,24 @@ class Agent:
         custom_instructions: str = "",
         update_func: Optional[Callable[[AgentStatusType, str], None]] = None,
     ) -> "Agent":
-        """Create an agent from tools, agent type, and language model.
+        """
+        Create an agent from tools, agent type, and language model.
 
         Args:
-        - tools (list[FunctionTool]): A list of tools to be used by the agent.
-        - topic (str, optional): The topic for the agent. Defaults to 'general'.
-        - custom_instructions (str, optional): custom instructions for the agent. Defaults to ''.
-        - llm (LLM): The language model to be used by the agent.
+
+            tools (list[FunctionTool]): A list of tools to be used by the agent.
+            topic (str, optional): The topic for the agent. Defaults to 'general'.
+            custom_instructions (str, optional): custom instructions for the agent. Defaults to ''.
+            llm (LLM): The language model to be used by the agent.
 
         Returns:
-        - Agent: An instance of the Agent class.
+            Agent: An instance of the Agent class.
         """
         return cls(tools, topic, custom_instructions, update_func)
 
     def report(self) -> str:
-        """Get a report from the agent.
+        """
+        Get a report from the agent.
 
         Returns:
             str: The report from the agent.
@@ -144,7 +153,8 @@ class Agent:
         wait_fixed=2000,
     )
     def chat(self, prompt: str) -> str:
-        """Interact with the agent using a chat prompt.
+        """
+        Interact with the agent using a chat prompt.
 
         Args:
             prompt (str): The chat prompt.

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/vectara_agentic/tools.py

@@ -51,7 +51,7 @@ LI_packages = {
 
 class VectaraTool:
     """
-    A wrapper of FunctionTOol class for Vectara tools, adding the tool_type attribute.
+    A wrapper of FunctionTool class for Vectara tools, adding the tool_type attribute.
     """
 
     def __init__(self, function_tool: FunctionTool, tool_type: ToolType) -> None:
@@ -137,7 +137,9 @@ class VectaraToolFactory:
 
         # Dynamically generate the RAG function
         def rag_function(*args, **kwargs) -> dict[str, Any]:
-            """Dynamically generated function for RAG query with Vectara"""
+            """
+            Dynamically generated function for RAG query with Vectara.
+            """
             # Convert args to kwargs using the function signature
             sig = inspect.signature(rag_function)
             bound_args = sig.bind_partial(*args, **kwargs)
@@ -253,7 +255,7 @@ class VectaraToolFactory:
 
 class ToolsFactory:
     """
-    A factory class for creating agent tools
+    A factory class for creating agent tools.
     """
 
     def create_tool(
@@ -267,7 +269,7 @@ class ToolsFactory:
             tool_type (ToolType): the type of tool.
 
         Returns:
-            list[FunctionTool]: a list of FunctionTool objects.
+            List[FunctionTool]: A list of FunctionTool objects.
         """
         return VectaraTool(FunctionTool.from_defaults(function), tool_type)
 
@@ -288,7 +290,7 @@ class ToolsFactory:
             kwargs (dict): The keyword arguments to pass to the tool constructor (see Hub for tool specific details).
 
         Returns:
-            list[FunctionTool]: a list of FunctionTool objects
+            list[FunctionTool]: A list of FunctionTool objects.
         """
         # Dynamically install and import the module
         if tool_package_name not in LI_packages.keys():
@@ -351,7 +353,7 @@ class ToolsFactory:
             text: str = Field(description="the original text."),
         ) -> str:
             """
-            critique the legal document.
+            Critique the legal document.
             """
             return critique_text(
                 text,
@@ -395,7 +397,7 @@ class ToolsFactory:
                You must specify either the sql_database object or the scheme, host, port, user, password, and dbname.
 
         Returns:
-            List[FunctionTool]: A list of FunctionTool objects
+            List[FunctionTool]: A list of FunctionTool objects.
         """
         if sql_database:
             tools = self.get_llama_index_tools(

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/vectara_agentic/tools_catalog.py

@@ -22,7 +22,6 @@ get_headers = {
 #
 # Standard Tools
 #
-
 def summarize_text(
     text: str = Field(description="the original text."),
     expertise: str = Field(
@@ -30,9 +29,16 @@ def summarize_text(
     ),
 ) -> str:
     """
-    This is a helper tool. It does not provide new information.
-    Use this tool to summarize text with no more than summary_max_length 
-    characters.
+    This is a helper tool. 
+    Use this tool to summarize text using a given expertise
+    with no more than summary_max_length characters.
+
+    Args:
+        text (str): The original text.
+        expertise (str): The expertise to apply to the summarization.
+    
+    Returns:
+        str: The summarized text.
     """
     expertise = "general" if len(expertise) < 3 else expertise.lower()
     prompt = f"As an expert in {expertise}, summarize the provided text"
@@ -50,9 +56,16 @@ def rephrase_text(
     ),
 ) -> str:
     """
-    This is a helper tool. It does not provide new information.
+    This is a helper tool. 
     Use this tool to rephrase the text according to the provided instructions.
     For example, instructions could be "as a 5 year old would say it."
+
+    Args:
+        text (str): The original text.
+        instructions (str): The specific instructions for how to rephrase the text.
+
+    Returns:    
+        str: The rephrased text.
     """
     prompt = f"""
     Rephrase the provided text according to the following instructions: {instructions}.
@@ -75,8 +88,16 @@ def critique_text(
     ),
 ) -> str:
     """
-    This is a helper tool. It does not provide new information.
+    This is a helper tool. 
     Critique the text from the specified point of view.
+
+    Args:
+        text (str): The original text.
+        role (str): The role of the person providing critique.
+        point_of_view (str): The point of view with which to provide critique.
+
+    Returns:
+        str: The critique of the text.
     """
     if role:
         prompt = f"As a {role}, critique the provided text from the point of view of {point_of_view}."
@@ -94,12 +115,16 @@ def critique_text(
 #
 # Guardrails tools
 #
-
-
 def guardrails_no_politics(text: str = Field(description="the original text.")) -> str:
     """
     A guardrails tool.
-    Can be used to rephrase text so that it does not have political content.
+    Given the input text, rephrases the text to ensure that the response avoids any specific political content.
+
+    Args:
+        text (str): The original text.
+
+    Returns:
+        str: The rephrased text.
     """
     return rephrase_text(text, "avoid any specific political content.")
 
@@ -107,6 +132,12 @@ def guardrails_no_politics(text: str = Field(description="the original text."))
 def guardrails_be_polite(text: str = Field(description="the original text.")) -> str:
     """
     A guardrails tool.
-    Can be used to rephrase the text so that the response is in a polite tone.
+    Given the input text, rephrases the text to ensure that the response is polite.
+
+    Args:
+        text (str): The original text.
+
+    Returns:
+        str: The rephrased text.
     """
     return rephrase_text(text, "Ensure the response is super polite.")

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2/vectara_agentic.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectara_agentic
-Version: 0.1.1
+Version: 0.1.2
 Summary: A Python package for creating AI Assistants and AI Agents with Vectara
 Home-page: https://github.com/vectara/py-vectara-agentic
 Author: Ofer Mendelevitch
@@ -31,6 +31,7 @@ Requires-Dist: mypy==1.11.0
 Requires-Dist: pylint==3.2.6
 Requires-Dist: flake8==7.1.0
 Requires-Dist: pymongo==4.6.1
+Requires-Dist: python-dotenv==1.0.1
 
 # vectara-agentic
 
@@ -138,15 +139,12 @@ mult_tool = ToolsFactory().create_tool(mult_func)
 
 ```python
 agent = Agent(
-    agent_type = agent_type,
     tools = tools,
     topic = topic_of_expertise
     custom_instructions = financial_bot_instructions,
     update_func = update_func
 )
 ```
-
-- `agent_type` is one of `AgentType.REACT` or `AgentTypeOpenAI`
 - `tools` is the list of tools you want to provide to the agent
 - `topic` is a string that defines the expertise you want the agent to specialize in.
 - `custom_instructions` is an optional string that defines special instructions to the agent
@@ -154,6 +152,8 @@ agent = Agent(
   The inputs to this function you provide are `status_type` of type AgentStatusType and 
   `msg` which is a string.
 
+Note that the Agent type (`OPENAI` or `REACT`) is defined as an environment variables `VECTARA_AGENTIC_AGENT_TYPE`.
+
 For example, for a financial agent we can use:
 
 ```python

{vectara_agentic-0.1.1 → vectara_agentic-0.1.2}/vectara_agentic.egg-info/requires.txt

@@ -18,3 +18,4 @@ mypy==1.11.0
 pylint==3.2.6
 flake8==7.1.0
 pymongo==4.6.1
+python-dotenv==1.0.1