vectara-agentic 0.2.4__tar.gz → 0.2.6__tar.gz

{vectara_agentic-0.2.4 → vectara_agentic-0.2.6}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.2.4
+Version: 0.2.6
 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
@@ -16,13 +16,13 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.22
-Requires-Dist: llama-index-indices-managed-vectara==0.4.1
+Requires-Dist: llama-index==0.12.25
+Requires-Dist: llama-index-indices-managed-vectara==0.4.2
 Requires-Dist: llama-index-agent-llm-compiler==0.3.0
 Requires-Dist: llama-index-agent-lats==0.3.0
 Requires-Dist: llama-index-agent-openai==0.4.6
 Requires-Dist: llama-index-llms-openai==0.3.25
-Requires-Dist: llama-index-llms-anthropic==0.6.7
+Requires-Dist: llama-index-llms-anthropic==0.6.10
 Requires-Dist: llama-index-llms-together==0.3.1
 Requires-Dist: llama-index-llms-groq==0.3.1
 Requires-Dist: llama-index-llms-fireworks==0.3.2
@@ -41,18 +41,18 @@ Requires-Dist: llama-index-tools-exa==0.3.0
 Requires-Dist: tavily-python==0.5.1
 Requires-Dist: exa-py==1.8.9
 Requires-Dist: yahoo-finance==1.4.0
-Requires-Dist: openinference-instrumentation-llama-index==3.1.4
-Requires-Dist: opentelemetry-proto==1.26.0
-Requires-Dist: arize-phoenix==7.11.0
-Requires-Dist: arize-phoenix-otel==0.6.1
-Requires-Dist: protobuf==4.25.5
+Requires-Dist: openinference-instrumentation-llama-index==3.3.3
+Requires-Dist: opentelemetry-proto==1.31.0
+Requires-Dist: arize-phoenix==8.14.1
+Requires-Dist: arize-phoenix-otel==0.8.0
+Requires-Dist: protobuf==5.29.3
 Requires-Dist: tokenizers>=0.20
-Requires-Dist: pydantic==2.10.3
+Requires-Dist: pydantic==2.10.6
 Requires-Dist: retrying==1.3.4
 Requires-Dist: python-dotenv==1.0.1
 Requires-Dist: tiktoken==0.9.0
 Requires-Dist: cloudpickle>=3.1.1
-Requires-Dist: httpx==0.27.2
+Requires-Dist: httpx==0.28.1
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -60,6 +60,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: keywords
+Dynamic: license-file
 Dynamic: project-url
 Dynamic: requires-dist
 Dynamic: requires-python
@@ -93,14 +94,20 @@ Dynamic: summary
 <img src="https://raw.githubusercontent.com/vectara/py-vectara-agentic/main/.github/assets/diagram1.png" alt="Agentic RAG diagram" width="100%" style="vertical-align: middle;">
 </p>
 
-###  Features
-
-- Enables easy creation of custom AI assistants and agents.
-- Create a Vectara RAG tool or search tool with a single line of code.
-- Supports `ReAct`, `OpenAIAgent`, `LATS` and `LLMCompiler` agent types.
-- Includes pre-built tools for various domains (e.g., finance, legal).
-- Integrates with various LLM inference services like OpenAI, Anthropic, Gemini, GROQ, Together.AI, Cohere, Bedrock and Fireworks
-- Built-in support for observability with Arize Phoenix
+### Key Features
+
+- **Rapid Tool Creation:**  
+  Build Vectara RAG tools or search tools with a single line of code.
+- **Agent Flexibility:**  
+  Supports multiple agent types including `ReAct`, `OpenAIAgent`, `LATS`, and `LLMCompiler`.
+- **Pre-Built Domain Tools:**  
+  Tools tailored for finance, legal, and other verticals.
+- **Multi-LLM Integration:**  
+  Seamless integration with OpenAI, Anthropic, Gemini, GROQ, Together.AI, Cohere, Bedrock, and Fireworks.
+- **Observability:**  
+  Built-in support with Arize Phoenix for monitoring and feedback.
+- **Workflow Support:**  
+  Extend your agent’s capabilities by defining custom workflows using the `run()` method.
 
 ### 📚 Example AI Assistants
 
@@ -200,7 +207,7 @@ agent = Agent(
 
 See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
 
-### 5. Run your agent
+### 5. Run a chat interaction
 
 ```python
 res = agent.chat("What was the revenue for Apple in 2021?")
@@ -213,6 +220,77 @@ Note that:
    response it's available as the `response` variable, or just use `str()`. For advanced use-cases you can look 
    at other `AgentResponse` variables [such as `sources`](https://github.com/run-llama/llama_index/blob/659f9faaafbecebb6e6c65f42143c0bf19274a37/llama-index-core/llama_index/core/chat_engine/types.py#L53).
 
+## Advanced Usage: Workflows
+
+In addition to standard chat interactions, `vectara-agentic` supports custom workflows via the `run()` method. 
+Workflows allow you to structure multi-step interactions where inputs and outputs are validated using Pydantic models.
+To learn more about workflows read [the documentation](https://docs.llamaindex.ai/en/stable/understanding/workflows/basic_flow/)
+
+### Defining a Custom Workflow
+
+Create a workflow by subclassing `llama_index.core.workflow.Workflow` and defining the input/output models:
+
+```python
+from pydantic import BaseModel
+from llama_index.core.workflow import (
+    StartEvent,StopEvent, Workflow, step,
+)
+
+class MyWorkflow(Workflow):
+    class InputsModel(BaseModel):
+        query: str
+
+    class OutputsModel(BaseModel):
+        answer: str
+
+    @step
+    async def my_step(self, ev: StartEvent) -> StopEvent:
+        # do something here
+        return StopEvent(result="Hello, world!")
+```
+
+When the `run()` method in vectara-agentic is invoked, it calls the workflow with the following variables in the StartEvent:
+* `agent`: the agent object used to call `run()` (self)
+* `tools`: the tools provided to the agent. Those can be used as needed in the flow.
+* `llm`: a pointer to a LlamaIndex llm, so it can be used in the workflow. For example, one of the steps may call `llm.acomplete(prompt)`
+* `verbose`: controls whether extra debug information is displayed
+* `inputs`: this is the actual inputs to the workflow provided by the call to `run()` and must be of type `InputsModel`
+
+### Using the Workflow with Your Agent
+
+When initializing your agent, pass the workflow class using the `workflow_cls` parameter:
+
+```python
+agent = Agent(
+    tools=[query_financial_reports_tool],
+    topic="10-K financial reports",
+    custom_instructions="You are a helpful financial assistant.",
+    workflow_cls=MyWorkflow,       # Provide your custom workflow here
+    workflow_timeout=120           # Optional: Set a timeout (default is 120 seconds)
+)
+```
+
+### Running the Workflow
+
+Prepare the inputs using your workflow’s `InputsModel` and execute the workflow using `run()`:
+
+```python
+# Create an instance of the workflow's input model
+inputs = MyWorkflow.InputsModel(query="What is Vectara?", extra_param=42)
+
+# Run the workflow (ensure you're in an async context or use asyncio.run)
+workflow_result = asyncio.run(agent.run(inputs))
+
+# Access the output from the workflow's OutputsModel
+print(workflow_result.answer)
+```
+
+### Using SubQuestionQueryWorkflow
+
+vectara-agentic already includes one useful workflow you can use right away (it is also useful as an advanced example)
+This workflow is called `SubQuestionQueryWorkflow` and it works by breaking a complex query into sub-queries and then
+executing each sub-query with the agent until it reaches a good response.
+
 ## 🧰 Vectara tools
 
 `vectara-agentic` provides two helper functions to connect with Vectara RAG
@@ -353,9 +431,9 @@ The `AgentConfig` object may include the following items:
 
 If any of these are not provided, `AgentConfig` first tries to read the values from the OS environment.
 
-## Configuring Vectara RAG or search tools
+## Configuring Vectara tools: rag_tool, or search_tool
 
-When creating a `VectaraToolFactory`, you can pass in a `vectara_api_key`, `vectara_customer_id`, and `vectara_corpus_id` to the factory. 
+When creating a `VectaraToolFactory`, you can pass in a `vectara_api_key`, and `vectara_corpus_key` to the factory. 
 
 If not passed in, it will be taken from the environment variables (`VECTARA_API_KEY` and `VECTARA_CORPUS_KEY`). Note that `VECTARA_CORPUS_KEY` can be a single KEY or a comma-separated list of KEYs (if you want to query multiple corpora).
 

vectara_agentic-0.2.4/vectara_agentic.egg-info/PKG-INFO → vectara_agentic-0.2.6/README.md

@@ -1,70 +1,3 @@
-Metadata-Version: 2.2
-Name: vectara_agentic
-Version: 0.2.4
-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
-Author-email: ofer@vectara.com
-Project-URL: Documentation, https://vectara.github.io/py-vectara-agentic/
-Keywords: LLM,NLP,RAG,Agentic-RAG,AI assistant,AI Agent,Vectara
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Operating System :: OS Independent
-Classifier: Development Status :: 4 - Beta
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: >=3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: llama-index==0.12.22
-Requires-Dist: llama-index-indices-managed-vectara==0.4.1
-Requires-Dist: llama-index-agent-llm-compiler==0.3.0
-Requires-Dist: llama-index-agent-lats==0.3.0
-Requires-Dist: llama-index-agent-openai==0.4.6
-Requires-Dist: llama-index-llms-openai==0.3.25
-Requires-Dist: llama-index-llms-anthropic==0.6.7
-Requires-Dist: llama-index-llms-together==0.3.1
-Requires-Dist: llama-index-llms-groq==0.3.1
-Requires-Dist: llama-index-llms-fireworks==0.3.2
-Requires-Dist: llama-index-llms-cohere==0.4.0
-Requires-Dist: llama-index-llms-gemini==0.4.11
-Requires-Dist: llama-index-llms-bedrock==0.3.4
-Requires-Dist: llama-index-tools-yahoo-finance==0.3.0
-Requires-Dist: llama-index-tools-arxiv==0.3.0
-Requires-Dist: llama-index-tools-database==0.3.0
-Requires-Dist: llama-index-tools-google==0.3.0
-Requires-Dist: llama-index-tools-tavily_research==0.3.0
-Requires-Dist: llama-index-tools-neo4j==0.3.0
-Requires-Dist: llama-index-graph-stores-kuzu==0.6.0
-Requires-Dist: llama-index-tools-slack==0.3.0
-Requires-Dist: llama-index-tools-exa==0.3.0
-Requires-Dist: tavily-python==0.5.1
-Requires-Dist: exa-py==1.8.9
-Requires-Dist: yahoo-finance==1.4.0
-Requires-Dist: openinference-instrumentation-llama-index==3.1.4
-Requires-Dist: opentelemetry-proto==1.26.0
-Requires-Dist: arize-phoenix==7.11.0
-Requires-Dist: arize-phoenix-otel==0.6.1
-Requires-Dist: protobuf==4.25.5
-Requires-Dist: tokenizers>=0.20
-Requires-Dist: pydantic==2.10.3
-Requires-Dist: retrying==1.3.4
-Requires-Dist: python-dotenv==1.0.1
-Requires-Dist: tiktoken==0.9.0
-Requires-Dist: cloudpickle>=3.1.1
-Requires-Dist: httpx==0.27.2
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: project-url
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
 # <img src="https://raw.githubusercontent.com/vectara/py-vectara-agentic/main/.github/assets/Vectara-logo.png" alt="Vectara Logo" width="30" height="30" style="vertical-align: middle;"> vectara-agentic
 
 <p align="center">
@@ -93,14 +26,20 @@ Dynamic: summary
 <img src="https://raw.githubusercontent.com/vectara/py-vectara-agentic/main/.github/assets/diagram1.png" alt="Agentic RAG diagram" width="100%" style="vertical-align: middle;">
 </p>
 
-###  Features
-
-- Enables easy creation of custom AI assistants and agents.
-- Create a Vectara RAG tool or search tool with a single line of code.
-- Supports `ReAct`, `OpenAIAgent`, `LATS` and `LLMCompiler` agent types.
-- Includes pre-built tools for various domains (e.g., finance, legal).
-- Integrates with various LLM inference services like OpenAI, Anthropic, Gemini, GROQ, Together.AI, Cohere, Bedrock and Fireworks
-- Built-in support for observability with Arize Phoenix
+### Key Features
+
+- **Rapid Tool Creation:**  
+  Build Vectara RAG tools or search tools with a single line of code.
+- **Agent Flexibility:**  
+  Supports multiple agent types including `ReAct`, `OpenAIAgent`, `LATS`, and `LLMCompiler`.
+- **Pre-Built Domain Tools:**  
+  Tools tailored for finance, legal, and other verticals.
+- **Multi-LLM Integration:**  
+  Seamless integration with OpenAI, Anthropic, Gemini, GROQ, Together.AI, Cohere, Bedrock, and Fireworks.
+- **Observability:**  
+  Built-in support with Arize Phoenix for monitoring and feedback.
+- **Workflow Support:**  
+  Extend your agent’s capabilities by defining custom workflows using the `run()` method.
 
 ### 📚 Example AI Assistants
 
@@ -200,7 +139,7 @@ agent = Agent(
 
 See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
 
-### 5. Run your agent
+### 5. Run a chat interaction
 
 ```python
 res = agent.chat("What was the revenue for Apple in 2021?")
@@ -213,6 +152,77 @@ Note that:
    response it's available as the `response` variable, or just use `str()`. For advanced use-cases you can look 
    at other `AgentResponse` variables [such as `sources`](https://github.com/run-llama/llama_index/blob/659f9faaafbecebb6e6c65f42143c0bf19274a37/llama-index-core/llama_index/core/chat_engine/types.py#L53).
 
+## Advanced Usage: Workflows
+
+In addition to standard chat interactions, `vectara-agentic` supports custom workflows via the `run()` method. 
+Workflows allow you to structure multi-step interactions where inputs and outputs are validated using Pydantic models.
+To learn more about workflows read [the documentation](https://docs.llamaindex.ai/en/stable/understanding/workflows/basic_flow/)
+
+### Defining a Custom Workflow
+
+Create a workflow by subclassing `llama_index.core.workflow.Workflow` and defining the input/output models:
+
+```python
+from pydantic import BaseModel
+from llama_index.core.workflow import (
+    StartEvent,StopEvent, Workflow, step,
+)
+
+class MyWorkflow(Workflow):
+    class InputsModel(BaseModel):
+        query: str
+
+    class OutputsModel(BaseModel):
+        answer: str
+
+    @step
+    async def my_step(self, ev: StartEvent) -> StopEvent:
+        # do something here
+        return StopEvent(result="Hello, world!")
+```
+
+When the `run()` method in vectara-agentic is invoked, it calls the workflow with the following variables in the StartEvent:
+* `agent`: the agent object used to call `run()` (self)
+* `tools`: the tools provided to the agent. Those can be used as needed in the flow.
+* `llm`: a pointer to a LlamaIndex llm, so it can be used in the workflow. For example, one of the steps may call `llm.acomplete(prompt)`
+* `verbose`: controls whether extra debug information is displayed
+* `inputs`: this is the actual inputs to the workflow provided by the call to `run()` and must be of type `InputsModel`
+
+### Using the Workflow with Your Agent
+
+When initializing your agent, pass the workflow class using the `workflow_cls` parameter:
+
+```python
+agent = Agent(
+    tools=[query_financial_reports_tool],
+    topic="10-K financial reports",
+    custom_instructions="You are a helpful financial assistant.",
+    workflow_cls=MyWorkflow,       # Provide your custom workflow here
+    workflow_timeout=120           # Optional: Set a timeout (default is 120 seconds)
+)
+```
+
+### Running the Workflow
+
+Prepare the inputs using your workflow’s `InputsModel` and execute the workflow using `run()`:
+
+```python
+# Create an instance of the workflow's input model
+inputs = MyWorkflow.InputsModel(query="What is Vectara?", extra_param=42)
+
+# Run the workflow (ensure you're in an async context or use asyncio.run)
+workflow_result = asyncio.run(agent.run(inputs))
+
+# Access the output from the workflow's OutputsModel
+print(workflow_result.answer)
+```
+
+### Using SubQuestionQueryWorkflow
+
+vectara-agentic already includes one useful workflow you can use right away (it is also useful as an advanced example)
+This workflow is called `SubQuestionQueryWorkflow` and it works by breaking a complex query into sub-queries and then
+executing each sub-query with the agent until it reaches a good response.
+
 ## 🧰 Vectara tools
 
 `vectara-agentic` provides two helper functions to connect with Vectara RAG
@@ -353,9 +363,9 @@ The `AgentConfig` object may include the following items:
 
 If any of these are not provided, `AgentConfig` first tries to read the values from the OS environment.
 
-## Configuring Vectara RAG or search tools
+## Configuring Vectara tools: rag_tool, or search_tool
 
-When creating a `VectaraToolFactory`, you can pass in a `vectara_api_key`, `vectara_customer_id`, and `vectara_corpus_id` to the factory. 
+When creating a `VectaraToolFactory`, you can pass in a `vectara_api_key`, and `vectara_corpus_key` to the factory. 
 
 If not passed in, it will be taken from the environment variables (`VECTARA_API_KEY` and `VECTARA_CORPUS_KEY`). Note that `VECTARA_CORPUS_KEY` can be a single KEY or a comma-separated list of KEYs (if you want to query multiple corpora).
 

{vectara_agentic-0.2.4 → vectara_agentic-0.2.6}/requirements.txt

@@ -1,10 +1,10 @@
-llama-index==0.12.22
-llama-index-indices-managed-vectara==0.4.1
+llama-index==0.12.25
+llama-index-indices-managed-vectara==0.4.2
 llama-index-agent-llm-compiler==0.3.0
 llama-index-agent-lats==0.3.0
 llama-index-agent-openai==0.4.6
 llama-index-llms-openai==0.3.25
-llama-index-llms-anthropic==0.6.7
+llama-index-llms-anthropic==0.6.10
 llama-index-llms-together==0.3.1
 llama-index-llms-groq==0.3.1
 llama-index-llms-fireworks==0.3.2
@@ -23,15 +23,15 @@ llama-index-tools-exa==0.3.0
 tavily-python==0.5.1
 exa-py==1.8.9
 yahoo-finance==1.4.0
-openinference-instrumentation-llama-index==3.1.4
-opentelemetry-proto==1.26.0
-arize-phoenix==7.11.0
-arize-phoenix-otel==0.6.1
-protobuf==4.25.5
+openinference-instrumentation-llama-index==3.3.3
+opentelemetry-proto==1.31.0
+arize-phoenix==8.14.1
+arize-phoenix-otel==0.8.0
+protobuf==5.29.3
 tokenizers>=0.20
-pydantic==2.10.3
+pydantic==2.10.6
 retrying==1.3.4
 python-dotenv==1.0.1
 tiktoken==0.9.0
 cloudpickle>=3.1.1
-httpx==0.27.2
+httpx==0.28.1

{vectara_agentic-0.2.4 → vectara_agentic-0.2.6}/tests/test_agent.py

@@ -102,8 +102,18 @@ class TestAgentPackage(unittest.TestCase):
         self.assertEqual(agent._topic, "question answering")
 
     def test_serialization(self):
+        config = AgentConfig(
+            agent_type=AgentType.REACT,
+            main_llm_provider=ModelProvider.ANTHROPIC,
+            main_llm_model_name="claude-3-5-sonnet-20241022",
+            tool_llm_provider=ModelProvider.TOGETHER,
+            tool_llm_model_name="meta-llama/Llama-3.3-70B-Instruct-Turbo",
+            observer=ObserverType.ARIZE_PHOENIX
+        )
+
         agent = Agent.from_corpus(
             tool_name="RAG Tool",
+            agent_config=config,
             vectara_corpus_key="corpus_key",
             vectara_api_key="api_key",
             data_description="information",
@@ -117,10 +127,18 @@ class TestAgentPackage(unittest.TestCase):
         self.assertEqual(agent, agent_reloaded)
         self.assertEqual(agent.agent_type, agent_reloaded.agent_type)
 
+        self.assertEqual(agent.agent_config.observer, agent_reloaded.agent_config.observer)
+        self.assertEqual(agent.agent_config.main_llm_provider, agent_reloaded.agent_config.main_llm_provider)
+        self.assertEqual(agent.agent_config.tool_llm_provider, agent_reloaded.agent_config.tool_llm_provider)
+
         self.assertIsInstance(agent_reloaded, Agent)
         self.assertEqual(agent, agent_reloaded_again)
         self.assertEqual(agent.agent_type, agent_reloaded_again.agent_type)
 
+        self.assertEqual(agent.agent_config.observer, agent_reloaded_again.agent_config.observer)
+        self.assertEqual(agent.agent_config.main_llm_provider, agent_reloaded_again.agent_config.main_llm_provider)
+        self.assertEqual(agent.agent_config.tool_llm_provider, agent_reloaded_again.agent_config.tool_llm_provider)
+
     def test_chat_history(self):
         tools = [ToolsFactory().create_tool(mult)]
         topic = "AI topic"

vectara_agentic-0.2.6/tests/test_agent_planning.py

@@ -0,0 +1,46 @@
+import unittest
+
+from vectara_agentic.agent import Agent
+from vectara_agentic.agent_config import AgentConfig
+from vectara_agentic.tools import ToolsFactory
+
+def mult(x, y):
+    return x * y
+
+def addition(x, y):
+    return x + y
+
+class TestAgentPlanningPackage(unittest.TestCase):
+
+    def test_no_planning(self):
+        tools = [ToolsFactory().create_tool(mult)]
+        topic = "AI topic"
+        instructions = "Always do as your father tells you, if your mother agrees!"
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig()
+        )
+
+        res = agent.chat("If you multiply 5 times 7, then 3 times 2, and add the results - what do you get?")
+        self.assertIn("41", res.response)
+
+    def test_structured_planning(self):
+        tools = [ToolsFactory().create_tool(mult), ToolsFactory().create_tool(addition)]
+        topic = "AI topic"
+        instructions = "Always do as your father tells you, if your mother agrees!"
+        agent = Agent(
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+            agent_config = AgentConfig(),
+            use_structured_planning = True,
+        )
+
+        res = agent.chat("If you multiply 5 times 7, then 3 times 2, and add the results - what do you get?")
+        self.assertIn("41", res.response)
+
+
+if __name__ == "__main__":
+    unittest.main()

vectara_agentic-0.2.6/tests/test_agent_type.py

@@ -0,0 +1,83 @@
+import unittest
+
+from vectara_agentic.agent import Agent, AgentType
+from vectara_agentic.agent_config import AgentConfig
+from vectara_agentic.tools import ToolsFactory
+from vectara_agentic.types import ModelProvider
+
+import nest_asyncio
+nest_asyncio.apply()
+def mult(x, y):
+    return x * y
+
+
+react_config_1 = AgentConfig(
+    agent_type=AgentType.REACT,
+    main_llm_provider=ModelProvider.ANTHROPIC,
+    main_llm_model_name="claude-3-7-sonnet-20250219",
+    tool_llm_provider=ModelProvider.TOGETHER,
+    tool_llm_model_name="meta-llama/Llama-3.3-70B-Instruct-Turbo",
+)
+
+react_config_2 = AgentConfig(
+    agent_type=AgentType.REACT,
+    main_llm_provider=ModelProvider.GEMINI,
+    tool_llm_provider=ModelProvider.GEMINI,
+)
+
+openai_config = AgentConfig(
+    agent_type=AgentType.OPENAI,
+)
+
+class TestAgentType(unittest.TestCase):
+
+    def test_openai(self):
+        tools = [ToolsFactory().create_tool(mult)]
+        topic = "AI topic"
+        instructions = "Always do as your father tells you, if your mother agrees!"
+        agent = Agent(
+            agent_config=openai_config,
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+        )
+
+        agent.chat("What is 5 times 10. Only give the answer, nothing else")
+        agent.chat("what is 3 times 7. Only give the answer, nothing else")
+        res = agent.chat("multiply the results of the last two multiplications. Only give the answer, nothing else.")
+        self.assertIn("1050", res.response)
+
+    def test_react_anthropic(self):
+        tools = [ToolsFactory().create_tool(mult)]
+        topic = "AI topic"
+        instructions = "Always do as your father tells you, if your mother agrees!"
+        agent = Agent(
+            agent_config=react_config_1,
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+        )
+
+        agent.chat("What is 5 times 10. Only give the answer, nothing else")
+        agent.chat("what is 3 times 7. Only give the answer, nothing else")
+        res = agent.chat("multiply the results of the last two multiplications. Only give the answer, nothing else.")
+        self.assertIn("1050", res.response)
+
+    def test_react_gemini(self):
+        tools = [ToolsFactory().create_tool(mult)]
+        topic = "AI topic"
+        instructions = "Always do as your father tells you, if your mother agrees!"
+        agent = Agent(
+            agent_config=react_config_2,
+            tools=tools,
+            topic=topic,
+            custom_instructions=instructions,
+        )
+        agent.chat("What is 5 times 10. Only give the answer, nothing else")
+        agent.chat("what is 3 times 7. Only give the answer, nothing else")
+        res = agent.chat("multiply the results of the last two multiplications. Only give the answer, nothing else.")
+        self.assertIn("1050", res.response)
+
+
+if __name__ == "__main__":
+    unittest.main()

vectara_agentic-0.2.6/tests/test_fallback.py

@@ -0,0 +1,83 @@
+import os
+import unittest
+import subprocess
+import time
+import requests
+import signal
+
+from vectara_agentic.agent import Agent, AgentType
+from vectara_agentic.agent_config import AgentConfig
+from vectara_agentic.types import ModelProvider, AgentConfigType
+from vectara_agentic.tools import ToolsFactory
+
+FLASK_PORT = 5002
+
+class TestFallback(unittest.TestCase):
+
+    @classmethod
+    def setUp(cls):
+        # Start the Flask server as a subprocess
+        cls.flask_process = subprocess.Popen(
+            ['flask', 'run', f'--port={FLASK_PORT}'],
+            env={**os.environ, 'FLASK_APP': 'tests.endpoint:app', 'FLASK_ENV': 'development'},
+            stdout=None, stderr=None,
+        )
+        # Wait for the server to start
+        timeout = 10
+        url = f'http://127.0.0.1:{FLASK_PORT}/'
+        for _ in range(timeout):
+            try:
+                requests.get(url)
+                print("Flask server started for fallback unit test")
+                return
+            except requests.ConnectionError:
+                time.sleep(1)
+        raise RuntimeError(f"Failed to start Flask server at {url}")
+
+    @classmethod
+    def tearDown(cls):
+        # Terminate the Flask server
+        cls.flask_process.send_signal(signal.SIGINT)
+        cls.flask_process.wait()
+
+    def test_fallback(self):
+        def mult(x, y):
+            return x * y
+
+        tools = [ToolsFactory().create_tool(mult)]
+        topic = "calculator"
+        custom_instructions = "you are an agent specializing in math, assisting a user."
+        config = AgentConfig(
+            agent_type=AgentType.REACT,
+            main_llm_provider=ModelProvider.PRIVATE,
+            main_llm_model_name="gpt-4o",
+            private_llm_api_base=f"http://127.0.0.1:{FLASK_PORT}/v1",
+            private_llm_api_key="TEST_API_KEY",
+        )
+
+        # Set fallback agent config to OpenAI agent
+        fallback_config = AgentConfig()
+
+        agent = Agent(agent_config=config, tools=tools, topic=topic,
+                      custom_instructions=custom_instructions,
+                      fallback_agent_config=fallback_config)
+
+        # To run this test, you must have OPENAI_API_KEY in your environment
+        res = agent.chat(
+            "What is 5 times 10. Only give the answer, nothing else"
+        ).response
+        self.assertEqual(res, "50")
+
+        TestFallback.flask_process.send_signal(signal.SIGINT)
+        TestFallback.flask_process.wait()
+
+        res = agent.chat(
+            "What is 5 times 10. Only give the answer, nothing else"
+        ).response
+        self.assertEqual(res, "50")
+        self.assertEqual(agent.agent_config_type, AgentConfigType.FALLBACK)
+        self.assertEqual(agent.fallback_agent_config, fallback_config)
+
+
+if __name__ == "__main__":
+    unittest.main()