vectara-agentic 0.2.9__tar.gz → 0.2.11__tar.gz

{vectara_agentic-0.2.9/vectara_agentic.egg-info → vectara_agentic-0.2.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.2.9
+Version: 0.2.11
 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
@@ -16,31 +16,31 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.26
+Requires-Dist: llama-index==0.12.29
 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-openai==0.3.32
 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
 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-llms-gemini==0.4.14
+Requires-Dist: llama-index-llms-bedrock==0.3.8
 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.brave_search==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-graph-stores-kuzu==0.7.0
 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: tavily-python==0.5.4
+Requires-Dist: exa-py==1.9.1
 Requires-Dist: openinference-instrumentation-llama-index==3.3.3
 Requires-Dist: opentelemetry-proto==1.31.0
 Requires-Dist: arize-phoenix==8.14.1
@@ -176,7 +176,7 @@ query_financial_reports_tool = vec_factory.create_rag_tool(
 )
 ```
 
-See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments to customize your Vectara RAG tool.
+See the [docs](https://vectara.github.io/py-vectara-agentic/latest/) for additional arguments to customize your Vectara RAG tool.
 
 ### 3. Create other tools (optional)
 
@@ -205,7 +205,7 @@ agent = Agent(
 )
 ```
 
-See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
+See the [docs](https://vectara.github.io/py-vectara-agentic/latest/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
 
 ### 5. Run a chat interaction
 
@@ -376,7 +376,7 @@ specified in the Agent configuration.
 - `load_unique_values`: returns the top unique values for a given column
 
 In addition, we include various other tools from LlamaIndex ToolSpecs:
-* Tavily search and EXA.AI
+* Tavily search, EXA.AI and Brave Search
 * arxiv
 * neo4j & Kuzu for Graph DB integration
 * Google tools (including gmail, calendar, and search)

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/README.md

@@ -108,7 +108,7 @@ query_financial_reports_tool = vec_factory.create_rag_tool(
 )
 ```
 
-See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments to customize your Vectara RAG tool.
+See the [docs](https://vectara.github.io/py-vectara-agentic/latest/) for additional arguments to customize your Vectara RAG tool.
 
 ### 3. Create other tools (optional)
 
@@ -137,7 +137,7 @@ agent = Agent(
 )
 ```
 
-See the [docs](https://vectara.github.io/vectara-agentic-docs/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
+See the [docs](https://vectara.github.io/py-vectara-agentic/latest/) for additional arguments, including `agent_progress_callback` and `query_logging_callback`.
 
 ### 5. Run a chat interaction
 
@@ -308,7 +308,7 @@ specified in the Agent configuration.
 - `load_unique_values`: returns the top unique values for a given column
 
 In addition, we include various other tools from LlamaIndex ToolSpecs:
-* Tavily search and EXA.AI
+* Tavily search, EXA.AI and Brave Search
 * arxiv
 * neo4j & Kuzu for Graph DB integration
 * Google tools (including gmail, calendar, and search)

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/requirements.txt

@@ -1,28 +1,28 @@
-llama-index==0.12.26
+llama-index==0.12.29
 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-openai==0.3.32
 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
 llama-index-llms-cohere==0.4.0
-llama-index-llms-gemini==0.4.11
-llama-index-llms-bedrock==0.3.4
+llama-index-llms-gemini==0.4.14
+llama-index-llms-bedrock==0.3.8
 llama-index-tools-yahoo-finance==0.3.0
 llama-index-tools-arxiv==0.3.0
 llama-index-tools-database==0.3.0
 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-graph-stores-kuzu==0.6.0
+llama-index-graph-stores-kuzu==0.7.0
 llama-index-tools-slack==0.3.0
 llama-index-tools-exa==0.3.0
-tavily-python==0.5.1
-exa-py==1.8.9
-yahoo-finance==1.4.0
+tavily-python==0.5.4
+exa-py==1.9.1
 openinference-instrumentation-llama-index==3.3.3
 opentelemetry-proto==1.31.0
 arize-phoenix==8.14.1

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/tests/test_tools.py

@@ -2,7 +2,12 @@ import unittest
 
 from pydantic import Field, BaseModel
 
-from vectara_agentic.tools import VectaraTool, VectaraToolFactory, ToolsFactory, ToolType
+from vectara_agentic.tools import (
+    VectaraTool,
+    VectaraToolFactory,
+    ToolsFactory,
+    ToolType,
+)
 from vectara_agentic.agent import Agent
 from vectara_agentic.agent_config import AgentConfig
 
@@ -13,9 +18,7 @@ class TestToolsPackage(unittest.TestCase):
     def test_vectara_tool_factory(self):
         vectara_corpus_key = "corpus_key"
         vectara_api_key = "api_key"
-        vec_factory = VectaraToolFactory(
-            vectara_corpus_key, vectara_api_key
-        )
+        vec_factory = VectaraToolFactory(vectara_corpus_key, vectara_api_key)
 
         self.assertEqual(vectara_corpus_key, vec_factory.vectara_corpus_key)
         self.assertEqual(vectara_api_key, vec_factory.vectara_api_key)
@@ -46,6 +49,48 @@ class TestToolsPackage(unittest.TestCase):
         self.assertIsInstance(search_tool, FunctionTool)
         self.assertEqual(search_tool.metadata.tool_type, ToolType.QUERY)
 
+    def test_vectara_tool_validation(self):
+        vectara_corpus_key = "corpus_key"
+        vectara_api_key = "api_key"
+        vec_factory = VectaraToolFactory(vectara_corpus_key, vectara_api_key)
+
+        class QueryToolArgs(BaseModel):
+            query: str = Field(description="The user query")
+            year: int = Field(
+                description="The year of the document",
+                example=2023,
+            )
+            ticker: str = Field(
+                description="The stock ticker",
+                example="AAPL",
+            )
+
+        query_tool = vec_factory.create_rag_tool(
+            tool_name="rag_tool",
+            tool_description="""
+            Returns a response (str) to the user query based on the data in this corpus.
+            """,
+            tool_args_schema=QueryToolArgs,
+        )
+        res = query_tool(
+            query="What is the stock price?",
+            the_year=2023,
+        )
+        self.assertIn("Malfunction", str(res))
+
+        search_tool = vec_factory.create_search_tool(
+            tool_name="search_tool",
+            tool_description="""
+            Returns a list of documents (str) that match the user query.
+            """,
+            tool_args_schema=QueryToolArgs,
+        )
+        res = search_tool(
+            query="What is the stock price?",
+            the_year=2023,
+        )
+        self.assertIn("Malfunction", str(res))
+
     def test_tool_factory(self):
         def mult(x: float, y: float) -> float:
             return x * y
@@ -59,17 +104,21 @@ class TestToolsPackage(unittest.TestCase):
     def test_llama_index_tools(self):
         tools_factory = ToolsFactory()
 
-        llama_tools = tools_factory.get_llama_index_tools(
-            tool_package_name="arxiv",
-            tool_spec_name="ArxivToolSpec"
-        )
-
-        arxiv_tool = llama_tools[0]
+        arxiv_tool = tools_factory.get_llama_index_tools(
+            tool_package_name="arxiv", tool_spec_name="ArxivToolSpec"
+        )[0]
 
         self.assertIsInstance(arxiv_tool, VectaraTool)
         self.assertIsInstance(arxiv_tool, FunctionTool)
         self.assertEqual(arxiv_tool.metadata.tool_type, ToolType.QUERY)
 
+        yfinance_tool = tools_factory.get_llama_index_tools(
+            tool_package_name="yahoo_finance", tool_spec_name="YahooFinanceToolSpec"
+        )[0]
+        self.assertIsInstance(yfinance_tool, VectaraTool)
+        self.assertIsInstance(yfinance_tool, FunctionTool)
+        self.assertEqual(yfinance_tool.metadata.tool_type, ToolType.QUERY)
+
     def test_public_repo(self):
         vectara_corpus_key = "vectara-docs_1"
         vectara_api_key = "zqt_UXrBcnI2UXINZkrv4g1tQPhzj02vfdtqYJIDiA"
@@ -80,10 +129,12 @@ class TestToolsPackage(unittest.TestCase):
             tool_name="ask_vectara",
             data_description="data from Vectara website",
             assistant_specialty="RAG as a service",
-            vectara_summarizer="mockingbird-1.0-2024-07-16"
+            vectara_summarizer="mockingbird-1.0-2024-07-16",
         )
 
-        self.assertIn("Vectara is an end-to-end platform", str(agent.chat("What is Vectara?")))
+        self.assertIn(
+            "Vectara is an end-to-end platform", str(agent.chat("What is Vectara?"))
+        )
 
     def test_class_method_as_tool(self):
         class TestClass:
@@ -102,7 +153,7 @@ class TestToolsPackage(unittest.TestCase):
             tools=tools,
             topic=topic,
             custom_instructions=instructions,
-            agent_config=config
+            agent_config=config,
         )
 
         self.assertEqual(

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/_callback.py

@@ -154,7 +154,7 @@ class AgentCallbackHandler(BaseCallbackHandler):
         elif event_type == CBEventType.AGENT_STEP:
             self._handle_agent_step(payload, event_id)
         elif event_type == CBEventType.EXCEPTION:
-            print(f"Exception: {payload.get(EventPayload.EXCEPTION)}")
+            print(f"Exception in handle_event: {payload.get(EventPayload.EXCEPTION)}")
         else:
             print(f"Unknown event type: {event_type}, payload={payload}")
 
@@ -168,7 +168,7 @@ class AgentCallbackHandler(BaseCallbackHandler):
         elif event_type == CBEventType.AGENT_STEP:
             await self._ahandle_agent_step(payload, event_id)
         elif event_type == CBEventType.EXCEPTION:
-            print(f"Exception: {payload.get(EventPayload.EXCEPTION)}")
+            print(f"Exception in ahandle_event: {payload.get(EventPayload.EXCEPTION)}")
         else:
             print(f"Unknown event type: {event_type}, payload={payload}")
 

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/_observability.py

@@ -8,7 +8,7 @@ import pandas as pd
 from .types import ObserverType
 from .agent_config import AgentConfig
 
-def setup_observer(config: AgentConfig) -> bool:
+def setup_observer(config: AgentConfig, verbose: bool) -> bool:
     '''
     Setup the observer.
     '''
@@ -31,7 +31,8 @@ def setup_observer(config: AgentConfig) -> bool:
             tracer_provider = register(endpoint=phoenix_endpoint, project_name="vectara-agentic")
         LlamaIndexInstrumentor().instrument(tracer_provider=tracer_provider)
         return True
-    print("No observer set.")
+    if verbose:
+        print("No observer set.")
     return False
 
 

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/_prompts.py

@@ -37,10 +37,11 @@ GENERAL_INSTRUCTIONS = """
 - If including latex equations in the markdown response, make sure the equations are on a separate line and enclosed in double dollar signs.
 - Always respond in the language of the question, and in text (no images, videos or code).
 - If you are provided with database tools use them for analytical queries (such as counting, calculating max, min, average, sum, or other statistics).
-  For each database, the database tools include: x_list_tables, x_load_data, x_describe_tables, and x_load_sample_data, where 'x' in the database name.
-  The x_list_tables tool provides a list of available tables in the x database. Always use x_list_tables before using other database tools, to understand valid table names.
-  Before using the x_load_data with a SQL query, always follow these steps:
-  - Use the x_describe_tables tool to understand the schema of each table.
+  For each database, the database tools include: x_list_tables, x_load_data, x_describe_tables, x_load_unique_values, and x_load_sample_data, where 'x' in the database name.
+  for example, if the database name is "ev", the tools are: ev_list_tables, ev_load_data, ev_describe_tables, ev_load_unique_values, and ev_load_sample_data.
+  Before using the x_load_data with a SQL query, always follow these discovery steps:
+  - call the x_list_tables tool to list of available tables in the x database.
+  - Call the x_describe_tables tool to understand the schema of each table you want to query data from.
   - Use the x_load_unique_values tool to understand the unique values in each column.
     Sometimes the user may ask for a specific column value, but the actual value in the table may be different, and you will need to use the correct value.
   - Use the x_load_sample_data tool to understand the column names, and typical values in each column.

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/_version.py

@@ -1,4 +1,4 @@
 """
 Define the version of the package.
 """
-__version__ = "0.2.9"
+__version__ = "0.2.11"

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/agent.py

@@ -252,7 +252,7 @@ class Agent:
 
         # Setup observability
         try:
-            self.observability_enabled = setup_observer(self.agent_config)
+            self.observability_enabled = setup_observer(self.agent_config, self.verbose)
         except Exception as e:
             print(f"Failed to set up observer ({e}), ignoring")
             self.observability_enabled = False

{vectara_agentic-0.2.9 → vectara_agentic-0.2.11}/vectara_agentic/db_tools.py

@@ -15,7 +15,6 @@ from sqlalchemy.engine import Engine
 from sqlalchemy.exc import NoSuchTableError
 from sqlalchemy.schema import CreateTable
 
-from llama_index.core.readers.base import BaseReader
 from llama_index.core.utilities.sql_wrapper import SQLDatabase
 from llama_index.core.schema import Document
 from llama_index.core.tools.function_tool import FunctionTool
@@ -25,7 +24,7 @@ from llama_index.core.tools.utils import create_schema_from_function
 
 AsyncCallable = Callable[..., Awaitable[Any]]
 
-class DatabaseTools(BaseReader):
+class DatabaseTools:
     """Database tools for vectara-agentic
     This class provides a set of tools to interact with a database.
     It allows you to load data, list tables, describe tables, and load unique values.
@@ -49,9 +48,11 @@ class DatabaseTools(BaseReader):
         user: Optional[str] = None,
         password: Optional[str] = None,
         dbname: Optional[str] = None,
+        tool_name_prefix: str = "db",
         **kwargs: Any,
     ) -> None:
         self.max_rows = max_rows
+        self.tool_name_prefix = tool_name_prefix
 
         if sql_database:
             self.sql_database = sql_database
@@ -86,35 +87,34 @@ class DatabaseTools(BaseReader):
             func = getattr(self, fn_name)
         except AttributeError:
             return None
-        name = fn_name
+        name = self.tool_name_prefix + "_" + fn_name if self.tool_name_prefix else fn_name
         docstring = func.__doc__ or ""
         description = f"{name}{signature(func)}\n{docstring}"
         fn_schema = create_schema_from_function(fn_name, getattr(self, fn_name))
         return ToolMetadata(name=name, description=description, fn_schema=fn_schema)
 
-    def _load_data(self, query: str) -> List[Document]:
+    def _load_data(self, sql_query: str) -> List[Document]:
         documents = []
         with self.sql_database.engine.connect() as connection:
-            if query is None:
+            if sql_query is None:
                 raise ValueError("A query parameter is necessary to filter the data")
-            result = connection.execute(text(query))
+            result = connection.execute(text(sql_query))
             for item in result.fetchall():
                 doc_str = ", ".join([str(entry) for entry in item])
                 documents.append(Document(text=doc_str))
         return documents
 
-    def load_data(self, *args: Any, **load_kwargs: Any) -> List[str]:
+    def load_data(self, sql_query: str) -> List[str]:
         """Query and load data from the Database, returning a list of Documents.
         Args:
-            query (str): an SQL query to filter tables and rows.
+            sql_query (str): an SQL query to filter tables and rows.
         Returns:
-            List[Document]: a list of Document objects from the database.
+            List[str]: a list of Document objects from the database.
         """
-        query = args[0] if args else load_kwargs.get("args",{}).get("query")
-        if query is None:
+        if sql_query is None:
             raise ValueError("A query parameter is necessary to filter the data")
 
-        count_query = f"SELECT COUNT(*) FROM ({query})"
+        count_query = f"SELECT COUNT(*) FROM ({sql_query})"
         try:
             count_rows = self._load_data(count_query)
         except Exception as e:
@@ -126,9 +126,9 @@ class DatabaseTools(BaseReader):
                 "Please refactor your query to make it return less rows. "
             ]
         try:
-            res = self._load_data(query)
+            res = self._load_data(sql_query)
         except Exception as e:
-            return [f"Error ({str(e)}) occurred while executing the query {query}"]
+            return [f"Error ({str(e)}) occurred while executing the query {sql_query}"]
         return [d.text for d in res]
 
     def load_sample_data(self, table_name: str, num_rows: int = 25) -> Any:
@@ -141,6 +141,11 @@ class DatabaseTools(BaseReader):
         Returns:
             Any: The result of the database query.
         """
+        if table_name not in self.list_tables():
+            return (
+                f"Table {table_name} does not exist in the database."
+                f"Valid table names are: {self.list_tables()}"
+            )
         try:
             res = self._load_data(f"SELECT * FROM {table_name} LIMIT {num_rows}")
         except Exception as e:
@@ -162,6 +167,15 @@ class DatabaseTools(BaseReader):
             str: A string representation of the table schemas.
         """
         table_names = tables or [table.name for table in self._metadata.sorted_tables]
+        if len(table_names) == 0:
+            return "You must specify at least one table name to describe."
+        for table_name in table_names:
+            if table_name not in self.list_tables():
+                return (
+                    f"Table {table_name} does not exist in the database."
+                    f"Valid table names are: {self.list_tables()}"
+                )
+
         table_schemas = []
         for table_name in table_names:
             table = next(
@@ -186,6 +200,12 @@ class DatabaseTools(BaseReader):
         Returns:
             Any: the result of the database query
         """
+        if table_name not in self.list_tables():
+            return (
+                f"Table {table_name} does not exist in the database."
+                f"Valid table names are: {self.list_tables()}"
+            )
+
         res = {}
         try:
             for column in columns: