vectara-agentic 0.2.16__tar.gz → 0.2.17__tar.gz

{vectara_agentic-0.2.16/vectara_agentic.egg-info → vectara_agentic-0.2.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.2.16
+Version: 0.2.17
 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
@@ -16,7 +16,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.34
+Requires-Dist: llama-index==0.12.35
 Requires-Dist: llama-index-indices-managed-vectara==0.4.5
 Requires-Dist: llama-index-agent-llm-compiler==0.3.0
 Requires-Dist: llama-index-agent-lats==0.3.0
@@ -36,15 +36,17 @@ Requires-Dist: llama-index-tools-google==0.3.0
 Requires-Dist: llama-index-tools-tavily_research==0.3.0
 Requires-Dist: llama_index.tools.brave_search==0.3.0
 Requires-Dist: llama-index-tools-neo4j==0.3.0
+Requires-Dist: llama-index-tools-waii==0.3.0
 Requires-Dist: llama-index-graph-stores-kuzu==0.7.0
+Requires-Dist: llama-index-tools-salesforce==0.3.0
 Requires-Dist: llama-index-tools-slack==0.3.0
 Requires-Dist: llama-index-tools-exa==0.3.0
 Requires-Dist: llama-index-tools-wikipedia==0.3.0
 Requires-Dist: llama-index-tools-bing-search==0.3.0
-Requires-Dist: tavily-python==0.5.4
-Requires-Dist: exa-py==1.12.0
+Requires-Dist: tavily-python==0.7.2
+Requires-Dist: exa-py==1.12.1
 Requires-Dist: openinference-instrumentation-llama-index==4.2.1
-Requires-Dist: opentelemetry-proto==1.32.1
+Requires-Dist: opentelemetry-proto>=1.31.0
 Requires-Dist: arize-phoenix==8.26.1
 Requires-Dist: arize-phoenix-otel==0.9.2
 Requires-Dist: protobuf==5.29.3
@@ -365,51 +367,92 @@ vectara-agentic includes various other tools from LlamaIndex ToolSpecs:
   * Tavily Search: Real-time web search using [Tavily API](https://tavily.com/)
     ```python
     from vectara_agentic.tools_catalog import ToolsCatalog
-    tavily_tool = ToolsCatalog(agent_config).tavily_search
+    tools_factory = ToolsFactory()
+    tavily_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="tavily_research",
+                    tool_spec_name="TavilyToolSpec",
+                    api_key=str(os.environ["TAVILY_API_KEY"]),
+                )
     ```
   * EXA.AI: Advanced web search and data extraction
     ```python
-    exa_tool = ToolsCatalog(agent_config).exa_search
+    exa_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="exa.ai",
+                    tool_spec_name="ExaToolSpec",
+                    api_key=str(os.environ["EXA_API_KEY"]),
+                )
     ```
   * Brave Search: Web search using Brave's search engine
     ```python
-    brave_tool = ToolsCatalog(agent_config).brave_search
+    brave_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="brave_search",
+                    tool_spec_name="BraveSearchToolSpec",
+                    api_key=str(os.environ["BRAVE_API_KEY"]),
+                )
     ```
 
 * **Academic Tools**
   * arXiv: Search and retrieve academic papers
     ```python
-    arxiv_tool = ToolsCatalog(agent_config).arxiv_search
+    arxiv_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="arxiv",
+                    tool_spec_name="ArxivToolSpec",
+                )
     ```
 
-* **Graph Database Tools**
+* **Database Tools**
   * Neo4j: Graph database integration
     ```python
-    neo4j_tool = ToolsCatalog(agent_config).neo4j_query
+    neo4j_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="neo4j",
+                    tool_spec_name="Neo4jQueryToolSpec",
+                )
     ```
   * Kuzu: Lightweight graph database
     ```python
-    kuzu_tool = ToolsCatalog(agent_config).kuzu_query
+    kuzu_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="kuzu",
+                    tool_spec_name="KuzuGraphStore",
+                )
+    ```
+  * Waii: tools for natural langauge query of a relational database
+    ```python
+    waii_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="waii",
+                    tool_spec_name="WaiiToolSpec",
+                )
     ```
 
 * **Google Tools**
   * Gmail: Read and send emails
     ```python
-    gmail_tool = ToolsCatalog(agent_config).gmail
+    gmail_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GmailToolSpec",
+                )
     ```
   * Calendar: Manage calendar events
     ```python
-    calendar_tool = ToolsCatalog(agent_config).calendar
+    calendar_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleCalendarToolSpec",
+                )
     ```
   * Search: Google search integration
     ```python
-    google_search_tool = ToolsCatalog(agent_config).google_search
+    search_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleSearchToolSpec",
+                )
     ```
 
 * **Communication Tools**
   * Slack: Send messages and interact with Slack
     ```python
-    slack_tool = ToolsCatalog(agent_config).slack
+    slack_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="slack",
+                    tool_spec_name="SlackToolSpec",
+                )
     ```
 
 For detailed setup instructions and API key requirements, please refer the instructions on [LlamaIndex hub](https://llamahub.ai/?tab=tools) for the specific tool.

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/README.md

@@ -295,51 +295,92 @@ vectara-agentic includes various other tools from LlamaIndex ToolSpecs:
   * Tavily Search: Real-time web search using [Tavily API](https://tavily.com/)
     ```python
     from vectara_agentic.tools_catalog import ToolsCatalog
-    tavily_tool = ToolsCatalog(agent_config).tavily_search
+    tools_factory = ToolsFactory()
+    tavily_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="tavily_research",
+                    tool_spec_name="TavilyToolSpec",
+                    api_key=str(os.environ["TAVILY_API_KEY"]),
+                )
     ```
   * EXA.AI: Advanced web search and data extraction
     ```python
-    exa_tool = ToolsCatalog(agent_config).exa_search
+    exa_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="exa.ai",
+                    tool_spec_name="ExaToolSpec",
+                    api_key=str(os.environ["EXA_API_KEY"]),
+                )
     ```
   * Brave Search: Web search using Brave's search engine
     ```python
-    brave_tool = ToolsCatalog(agent_config).brave_search
+    brave_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="brave_search",
+                    tool_spec_name="BraveSearchToolSpec",
+                    api_key=str(os.environ["BRAVE_API_KEY"]),
+                )
     ```
 
 * **Academic Tools**
   * arXiv: Search and retrieve academic papers
     ```python
-    arxiv_tool = ToolsCatalog(agent_config).arxiv_search
+    arxiv_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="arxiv",
+                    tool_spec_name="ArxivToolSpec",
+                )
     ```
 
-* **Graph Database Tools**
+* **Database Tools**
   * Neo4j: Graph database integration
     ```python
-    neo4j_tool = ToolsCatalog(agent_config).neo4j_query
+    neo4j_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="neo4j",
+                    tool_spec_name="Neo4jQueryToolSpec",
+                )
     ```
   * Kuzu: Lightweight graph database
     ```python
-    kuzu_tool = ToolsCatalog(agent_config).kuzu_query
+    kuzu_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="kuzu",
+                    tool_spec_name="KuzuGraphStore",
+                )
+    ```
+  * Waii: tools for natural langauge query of a relational database
+    ```python
+    waii_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="waii",
+                    tool_spec_name="WaiiToolSpec",
+                )
     ```
 
 * **Google Tools**
   * Gmail: Read and send emails
     ```python
-    gmail_tool = ToolsCatalog(agent_config).gmail
+    gmail_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GmailToolSpec",
+                )
     ```
   * Calendar: Manage calendar events
     ```python
-    calendar_tool = ToolsCatalog(agent_config).calendar
+    calendar_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleCalendarToolSpec",
+                )
     ```
   * Search: Google search integration
     ```python
-    google_search_tool = ToolsCatalog(agent_config).google_search
+    search_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleSearchToolSpec",
+                )
     ```
 
 * **Communication Tools**
   * Slack: Send messages and interact with Slack
     ```python
-    slack_tool = ToolsCatalog(agent_config).slack
+    slack_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="slack",
+                    tool_spec_name="SlackToolSpec",
+                )
     ```
 
 For detailed setup instructions and API key requirements, please refer the instructions on [LlamaIndex hub](https://llamahub.ai/?tab=tools) for the specific tool.

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/requirements.txt

@@ -1,4 +1,4 @@
-llama-index==0.12.34
+llama-index==0.12.35
 llama-index-indices-managed-vectara==0.4.5
 llama-index-agent-llm-compiler==0.3.0
 llama-index-agent-lats==0.3.0
@@ -18,15 +18,17 @@ llama-index-tools-google==0.3.0
 llama-index-tools-tavily_research==0.3.0
 llama_index.tools.brave_search==0.3.0
 llama-index-tools-neo4j==0.3.0
+llama-index-tools-waii==0.3.0
 llama-index-graph-stores-kuzu==0.7.0
+llama-index-tools-salesforce==0.3.0
 llama-index-tools-slack==0.3.0
 llama-index-tools-exa==0.3.0
 llama-index-tools-wikipedia==0.3.0
 llama-index-tools-bing-search==0.3.0
-tavily-python==0.5.4
-exa-py==1.12.0
+tavily-python==0.7.2
+exa-py==1.12.1
 openinference-instrumentation-llama-index==4.2.1
-opentelemetry-proto==1.32.1
+opentelemetry-proto>=1.31.0
 arize-phoenix==8.26.1
 arize-phoenix-otel==0.9.2
 protobuf==5.29.3

vectara_agentic-0.2.17/tests/test_workflow.py

@@ -0,0 +1,134 @@
+import unittest
+
+from pydantic import BaseModel
+
+from llama_index.core.workflow import WorkflowTimeoutError
+
+from vectara_agentic.agent import Agent
+from vectara_agentic.agent_config import AgentConfig
+from vectara_agentic.tools import ToolsFactory
+from vectara_agentic.sub_query_workflow import SubQuestionQueryWorkflow, SequentialSubQuestionsWorkflow
+
+def mult(x: float, y: float):
+    """
+    Multiply two numbers.
+    """
+    return x * y
+
+def add(x: float, y: float):
+    """
+    Add two numbers.
+    """
+    return x + y
+
+class TestWorkflowPackage(unittest.IsolatedAsyncioTestCase):
+
+    async def test_sub_query_workflow(self):
+        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
+        topic = "AI topic"
+        instructions = "You are a helpful AI assistant."
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig(),
+            workflow_cls = SubQuestionQueryWorkflow,
+        )
+
+        inputs = SubQuestionQueryWorkflow.InputsModel(
+            query="Compute 5 times 3, then add 7 to the result."
+        )
+        res = await agent.run(inputs=inputs)
+        self.assertIn("22", res.response)
+
+        inputs = SubQuestionQueryWorkflow.InputsModel(
+            query="what is the sum of 10 with 21, and the multiplication of 3 and 6?"
+        )
+        res = await agent.run(inputs=inputs)
+        self.assertIn("31", res.response)
+        self.assertIn("18", res.response)
+
+    async def test_seq_sub_query_workflow(self):
+        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
+        topic = "AI topic"
+        instructions = "You are a helpful AI assistant."
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig(),
+            workflow_cls = SequentialSubQuestionsWorkflow,
+        )
+
+        inputs = SequentialSubQuestionsWorkflow.InputsModel(
+            query="Compute 5 times 3, then add 7 to the result."
+        )
+        res = await agent.run(inputs=inputs, verbose=True)
+        self.assertIn("22", res.response)
+
+class TestWorkflowFailure(unittest.IsolatedAsyncioTestCase):
+
+    async def test_workflow_failure(self):
+        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
+        topic = "AI topic"
+        instructions = "You are a helpful AI assistant."
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig(),
+            workflow_cls = SubQuestionQueryWorkflow,
+            workflow_timeout = 1
+        )
+
+        inputs = SubQuestionQueryWorkflow.InputsModel(
+            query="Compute 5 times 3, then add 7 to the result."
+        )
+
+        res = None
+
+        try:
+            res = await agent.run(inputs=inputs)
+        except Exception as e:
+            self.assertIsInstance(e, WorkflowTimeoutError)
+
+        self.assertIsNone(res)
+
+    async def test_workflow_with_fail_class(self):
+        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
+        topic = "AI topic"
+        instructions = "You are a helpful AI assistant."
+
+        class SubQuestionQueryWorkflowWithFailClass(SubQuestionQueryWorkflow):
+            class OutputModelOnFail(BaseModel):
+                """
+                In case of failure, returns the user's original query
+                """
+                original_query: str
+
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig(),
+            workflow_cls = SubQuestionQueryWorkflowWithFailClass,
+            workflow_timeout = 1
+        )
+
+        inputs = SubQuestionQueryWorkflow.InputsModel(
+            query="Compute 5 times 3, then add 7 to the result."
+        )
+
+        res = None
+
+        try:
+            res = await agent.run(inputs=inputs)
+        except Exception as e:
+            assert isinstance(e, WorkflowTimeoutError)
+
+        self.assertIsInstance(res, SubQuestionQueryWorkflowWithFailClass.OutputModelOnFail)
+        self.assertEqual(res.original_query, "Compute 5 times 3, then add 7 to the result.")
+
+
+if __name__ == "__main__":
+    unittest.main()

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/_version.py

@@ -1,4 +1,4 @@
 """
 Define the version of the package.
 """
-__version__ = "0.2.16"
+__version__ = "0.2.17"

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/agent.py

@@ -35,7 +35,7 @@ from llama_index.core.callbacks.base_handler import BaseCallbackHandler
 from llama_index.agent.openai import OpenAIAgent
 from llama_index.core.agent.runner.base import AgentRunner
 from llama_index.core.agent.types import BaseAgent
-from llama_index.core.workflow import Workflow
+from llama_index.core.workflow import Workflow, Context
 
 from .types import (
     AgentType,
@@ -198,7 +198,7 @@ class Agent:
 
     def __init__(
         self,
-        tools: list[FunctionTool],
+        tools: List[FunctionTool],
         topic: str = "general",
         custom_instructions: str = "",
         general_instructions: str = GENERAL_INSTRUCTIONS,
@@ -213,7 +213,7 @@ class Agent:
         fallback_agent_config: Optional[AgentConfig] = None,
         chat_history: Optional[list[Tuple[str, str]]] = None,
         validate_tools: bool = False,
-        workflow_cls: Workflow = None,
+        workflow_cls: Optional[Workflow] = None,
         workflow_timeout: int = 120,
     ) -> None:
         """
@@ -287,10 +287,10 @@ class Agent:
             A tool is invalid if it is mentioned in the instructions but not in the tools list.
             A tool's name must have at least two characters.
             Your response should be a comma-separated list of the invalid tools.
-            If not invalid tools exist, respond with "<OKAY>".
+            If no invalid tools exist, respond with "<OKAY>" (and nothing else).
             """
             llm = get_llm(LLMRole.MAIN, config=self.agent_config)
-            bad_tools_str = llm.complete(prompt).text
+            bad_tools_str = llm.complete(prompt).text.strip('\n')
             if bad_tools_str and bad_tools_str != "<OKAY>":
                 bad_tools = [tool.strip() for tool in bad_tools_str.split(",")]
                 numbered = ", ".join(
@@ -643,7 +643,7 @@ class Agent:
         validate_tools: bool = False,
         fallback_agent_config: Optional[AgentConfig] = None,
         chat_history: Optional[list[Tuple[str, str]]] = None,
-        workflow_cls: Workflow = None,
+        workflow_cls: Optional[Workflow] = None,
         workflow_timeout: int = 120,
     ) -> "Agent":
         """
@@ -712,8 +712,8 @@ class Agent:
         vectara_rerank_limit: Optional[int] = None,
         vectara_rerank_cutoff: Optional[float] = None,
         vectara_diversity_bias: float = 0.2,
-        vectara_udf_expression: str = None,
-        vectara_rerank_chain: List[Dict] = None,
+        vectara_udf_expression: Optional[str] = None,
+        vectara_rerank_chain: Optional[List[Dict]] = None,
         vectara_n_sentences_before: int = 2,
         vectara_n_sentences_after: int = 2,
         vectara_summary_num_results: int = 10,
@@ -1047,7 +1047,7 @@ class Agent:
                 time.sleep(1)
                 attempt += 1
 
-        return AgentResponse(
+        return AgentStreamingResponse(
             response=(
                 f"For {orig_llm} LLM - failure can't be resolved after "
                 f"{max_attempts} attempts ({last_error})."
@@ -1059,7 +1059,11 @@ class Agent:
     # workflow will always get these arguments in the StartEvent: agent, tools, llm, verbose
     # the inputs argument comes from the call to run()
     #
-    async def run(self, inputs: Any, verbose: bool = False) -> Any:
+    async def run(
+        self,
+        inputs: Any,
+        verbose: bool = False,
+    ) -> Any:
         """
         Run a workflow using the agent.
         workflow class must be provided in the agent constructor.
@@ -1067,7 +1071,7 @@ class Agent:
             inputs (Any): The inputs to the workflow.
             verbose (bool, optional): Whether to print verbose output. Defaults to False.
         Returns:
-            Any: The output of the workflow.
+            Any: The output or context of the workflow.
         """
         # Create workflow
         if self.workflow_cls:
@@ -1079,20 +1083,38 @@ class Agent:
         if not isinstance(inputs, self.workflow_cls.InputsModel):
             raise ValueError(f"Inputs must be an instance of {workflow.InputsModel}.")
 
-        # run workflow
-        result = await workflow.run(
-            agent=self,
-            tools=self.tools,
-            llm=self.llm,
-            verbose=verbose,
-            inputs=inputs,
-        )
-
-        # return output in the form of workflow.OutputsModel
+        workflow_context = Context(workflow=workflow)
         try:
-            output = workflow.OutputsModel.model_validate(result)
-        except ValidationError as e:
-            raise ValueError(f"Failed to map workflow output to model: {e}") from e
+            # run workflow
+            result = await workflow.run(
+                ctx=workflow_context,
+                agent=self,
+                tools=self.tools,
+                llm=self.llm,
+                verbose=verbose,
+                inputs=inputs,
+            )
+
+            # return output in the form of workflow.OutputsModel(BaseModel)
+            try:
+                output = workflow.OutputsModel.model_validate(result)
+            except ValidationError as e:
+                raise ValueError(f"Failed to map workflow output to model: {e}") from e
+
+        except Exception as e:
+            outputs_model_on_fail_cls = getattr(workflow.__class__, "OutputModelOnFail", None)
+            if outputs_model_on_fail_cls:
+                model_fields = outputs_model_on_fail_cls.model_fields
+                input_dict = {
+                    key: await workflow_context.get(key, None)
+                    for key in model_fields
+                }
+
+                # return output in the form of workflow.OutputModelOnFail(BaseModel)
+                output = outputs_model_on_fail_cls.model_validate(input_dict)
+            else:
+                print(f"Vectara Agentic: Workflow failed with unexpected error: {e}")
+                raise type(e)(str(e)).with_traceback(e.__traceback__)
 
         return output
 
@@ -1117,12 +1139,12 @@ class Agent:
                 fn_schema_serialized = {
                     "schema": (
                         fn_schema_cls.model_json_schema()
-                        if hasattr(fn_schema_cls, "model_json_schema")
+                        if fn_schema_cls and hasattr(fn_schema_cls, "model_json_schema")
                         else None
                     ),
                     "metadata": {
-                        "module": fn_schema_cls.__module__,
-                        "class": fn_schema_cls.__name__,
+                        "module": fn_schema_cls.__module__ if fn_schema_cls else None,
+                        "class": fn_schema_cls.__name__ if fn_schema_cls else None,
                     },
                 }
             else:
@@ -1171,7 +1193,7 @@ class Agent:
             if data.get("fallback_agent_config")
             else None
         )
-        tools = []
+        tools: list[FunctionTool] = []
 
         for tool_data in data["tools"]:
             query_args_model = None

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/sub_query_workflow.py

@@ -50,7 +50,7 @@ class SubQuestionQueryWorkflow(Workflow):
         answer: str
 
     @step
-    async def query(self, ctx: Context, ev: StartEvent) -> QueryEvent:
+    async def query(self, ctx: Context, ev: StartEvent) -> QueryEvent | None:
         """
         Given a user question, and a list of tools, output a list of relevant
         sub-questions, such that the answers to all the sub-questions put together
@@ -130,7 +130,10 @@ class SubQuestionQueryWorkflow(Workflow):
         if sub_questions is None:
             raise ValueError(f"Invalid LLM response format: {response_str}")
         if not sub_questions:
-            raise ValueError("LLM returned empty sub-questions list")
+            # If the LLM returns an empty list, we need to handle it gracefully
+            # We use the original query as a single question fallback
+            print("LLM returned empty sub-questions list")
+            sub_questions = [original_query]
 
         await ctx.set("sub_question_count", len(sub_questions))
         for question in sub_questions:

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/tool_utils.py

@@ -112,6 +112,7 @@ class VectaraTool(FunctionTool):
         tool_metadata: Optional[ToolMetadata] = None,
         callback: Optional[Callable[[Any], Any]] = None,
         async_callback: Optional[AsyncCallable] = None,
+        partial_params: Optional[Dict[str, Any]] = None,
         tool_type: ToolType = ToolType.QUERY,
     ) -> "VectaraTool":
         tool = FunctionTool.from_defaults(
@@ -124,6 +125,7 @@ class VectaraTool(FunctionTool):
             tool_metadata,
             callback,
             async_callback,
+            partial_params
         )
         vectara_tool = cls(
             tool_type=tool_type,

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/tools.py

@@ -36,6 +36,8 @@ LI_packages = {
     "bing_search": ToolType.QUERY,
     "neo4j": ToolType.QUERY,
     "kuzu": ToolType.QUERY,
+    "waii": ToolType.QUERY,
+    "salesforce": ToolType.QUERY,
     "wikipedia": ToolType.QUERY,
     "google": {
         "GmailToolSpec": {

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic/utils.py

@@ -68,7 +68,7 @@ async def summarize_documents(
     api_key: str,
     doc_ids: list[str],
     llm_name: str = "gpt-4o",
-) -> dict[str, str]:
+) -> dict[str, str | BaseException]:
     """
     Summarize multiple documents in a Vectara corpus using the Vectara API.
     """

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17/vectara_agentic.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.2.16
+Version: 0.2.17
 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
@@ -16,7 +16,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.34
+Requires-Dist: llama-index==0.12.35
 Requires-Dist: llama-index-indices-managed-vectara==0.4.5
 Requires-Dist: llama-index-agent-llm-compiler==0.3.0
 Requires-Dist: llama-index-agent-lats==0.3.0
@@ -36,15 +36,17 @@ Requires-Dist: llama-index-tools-google==0.3.0
 Requires-Dist: llama-index-tools-tavily_research==0.3.0
 Requires-Dist: llama_index.tools.brave_search==0.3.0
 Requires-Dist: llama-index-tools-neo4j==0.3.0
+Requires-Dist: llama-index-tools-waii==0.3.0
 Requires-Dist: llama-index-graph-stores-kuzu==0.7.0
+Requires-Dist: llama-index-tools-salesforce==0.3.0
 Requires-Dist: llama-index-tools-slack==0.3.0
 Requires-Dist: llama-index-tools-exa==0.3.0
 Requires-Dist: llama-index-tools-wikipedia==0.3.0
 Requires-Dist: llama-index-tools-bing-search==0.3.0
-Requires-Dist: tavily-python==0.5.4
-Requires-Dist: exa-py==1.12.0
+Requires-Dist: tavily-python==0.7.2
+Requires-Dist: exa-py==1.12.1
 Requires-Dist: openinference-instrumentation-llama-index==4.2.1
-Requires-Dist: opentelemetry-proto==1.32.1
+Requires-Dist: opentelemetry-proto>=1.31.0
 Requires-Dist: arize-phoenix==8.26.1
 Requires-Dist: arize-phoenix-otel==0.9.2
 Requires-Dist: protobuf==5.29.3
@@ -365,51 +367,92 @@ vectara-agentic includes various other tools from LlamaIndex ToolSpecs:
   * Tavily Search: Real-time web search using [Tavily API](https://tavily.com/)
     ```python
     from vectara_agentic.tools_catalog import ToolsCatalog
-    tavily_tool = ToolsCatalog(agent_config).tavily_search
+    tools_factory = ToolsFactory()
+    tavily_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="tavily_research",
+                    tool_spec_name="TavilyToolSpec",
+                    api_key=str(os.environ["TAVILY_API_KEY"]),
+                )
     ```
   * EXA.AI: Advanced web search and data extraction
     ```python
-    exa_tool = ToolsCatalog(agent_config).exa_search
+    exa_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="exa.ai",
+                    tool_spec_name="ExaToolSpec",
+                    api_key=str(os.environ["EXA_API_KEY"]),
+                )
     ```
   * Brave Search: Web search using Brave's search engine
     ```python
-    brave_tool = ToolsCatalog(agent_config).brave_search
+    brave_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="brave_search",
+                    tool_spec_name="BraveSearchToolSpec",
+                    api_key=str(os.environ["BRAVE_API_KEY"]),
+                )
     ```
 
 * **Academic Tools**
   * arXiv: Search and retrieve academic papers
     ```python
-    arxiv_tool = ToolsCatalog(agent_config).arxiv_search
+    arxiv_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="arxiv",
+                    tool_spec_name="ArxivToolSpec",
+                )
     ```
 
-* **Graph Database Tools**
+* **Database Tools**
   * Neo4j: Graph database integration
     ```python
-    neo4j_tool = ToolsCatalog(agent_config).neo4j_query
+    neo4j_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="neo4j",
+                    tool_spec_name="Neo4jQueryToolSpec",
+                )
     ```
   * Kuzu: Lightweight graph database
     ```python
-    kuzu_tool = ToolsCatalog(agent_config).kuzu_query
+    kuzu_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="kuzu",
+                    tool_spec_name="KuzuGraphStore",
+                )
+    ```
+  * Waii: tools for natural langauge query of a relational database
+    ```python
+    waii_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="waii",
+                    tool_spec_name="WaiiToolSpec",
+                )
     ```
 
 * **Google Tools**
   * Gmail: Read and send emails
     ```python
-    gmail_tool = ToolsCatalog(agent_config).gmail
+    gmail_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GmailToolSpec",
+                )
     ```
   * Calendar: Manage calendar events
     ```python
-    calendar_tool = ToolsCatalog(agent_config).calendar
+    calendar_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleCalendarToolSpec",
+                )
     ```
   * Search: Google search integration
     ```python
-    google_search_tool = ToolsCatalog(agent_config).google_search
+    search_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="google",
+                    tool_spec_name="GoogleSearchToolSpec",
+                )
     ```
 
 * **Communication Tools**
   * Slack: Send messages and interact with Slack
     ```python
-    slack_tool = ToolsCatalog(agent_config).slack
+    slack_tools = tools_factory.get_llama_index_tools(
+                    tool_package_name="slack",
+                    tool_spec_name="SlackToolSpec",
+                )
     ```
 
 For detailed setup instructions and API key requirements, please refer the instructions on [LlamaIndex hub](https://llamahub.ai/?tab=tools) for the specific tool.

{vectara_agentic-0.2.16 → vectara_agentic-0.2.17}/vectara_agentic.egg-info/requires.txt

@@ -1,4 +1,4 @@
-llama-index==0.12.34
+llama-index==0.12.35
 llama-index-indices-managed-vectara==0.4.5
 llama-index-agent-llm-compiler==0.3.0
 llama-index-agent-lats==0.3.0
@@ -18,15 +18,17 @@ llama-index-tools-google==0.3.0
 llama-index-tools-tavily_research==0.3.0
 llama_index.tools.brave_search==0.3.0
 llama-index-tools-neo4j==0.3.0
+llama-index-tools-waii==0.3.0
 llama-index-graph-stores-kuzu==0.7.0
+llama-index-tools-salesforce==0.3.0
 llama-index-tools-slack==0.3.0
 llama-index-tools-exa==0.3.0
 llama-index-tools-wikipedia==0.3.0
 llama-index-tools-bing-search==0.3.0
-tavily-python==0.5.4
-exa-py==1.12.0
+tavily-python==0.7.2
+exa-py==1.12.1
 openinference-instrumentation-llama-index==4.2.1
-opentelemetry-proto==1.32.1
+opentelemetry-proto>=1.31.0
 arize-phoenix==8.26.1
 arize-phoenix-otel==0.9.2
 protobuf==5.29.3

vectara_agentic-0.2.16/tests/test_workflow.py

@@ -1,67 +0,0 @@
-import unittest
-
-from vectara_agentic.agent import Agent
-from vectara_agentic.agent_config import AgentConfig
-from vectara_agentic.tools import ToolsFactory
-from vectara_agentic.sub_query_workflow import SubQuestionQueryWorkflow, SequentialSubQuestionsWorkflow
-
-def mult(x: float, y: float):
-    """
-    Multiply two numbers.
-    """
-    return x * y
-
-def add(x: float, y: float):
-    """
-    Add two numbers.
-    """
-    return x + y
-
-class TestWorkflowPackage(unittest.IsolatedAsyncioTestCase):
-
-    async def test_sub_query_workflow(self):
-        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
-        topic = "AI topic"
-        instructions = "You are a helpful AI assistant."
-        agent = Agent(
-            tools=tools,
-            topic=topic,
-            custom_instructions=instructions,
-            agent_config = AgentConfig(),
-            workflow_cls = SubQuestionQueryWorkflow,
-        )
-
-        inputs = SubQuestionQueryWorkflow.InputsModel(
-            query="Compute 5 times 3, then add 7 to the result."
-        )
-        res = await agent.run(inputs=inputs)
-        self.assertIn("22", res.response)
-
-        inputs = SubQuestionQueryWorkflow.InputsModel(
-            query="what is the sum of 10 with 21, and the multiplication of 3 and 6?"
-        )
-        res = await agent.run(inputs=inputs)
-        self.assertIn("31", res.response)
-        self.assertIn("18", res.response)
-
-    async def test_seq_sub_query_workflow(self):
-        tools = [ToolsFactory().create_tool(mult)] + [ToolsFactory().create_tool(add)]
-        topic = "AI topic"
-        instructions = "You are a helpful AI assistant."
-        agent = Agent(
-            tools=tools,
-            topic=topic,
-            custom_instructions=instructions,
-            agent_config = AgentConfig(),
-            workflow_cls = SequentialSubQuestionsWorkflow,
-        )
-
-        inputs = SequentialSubQuestionsWorkflow.InputsModel(
-            query="Compute 5 times 3, then add 7 to the result."
-        )
-        res = await agent.run(inputs=inputs, verbose=True)
-        self.assertIn("22", res.response)
-
-
-if __name__ == "__main__":
-    unittest.main()