vectara-agentic 0.1.8__tar.gz → 0.1.9__tar.gz

{vectara_agentic-0.1.8/vectara_agentic.egg-info → vectara_agentic-0.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectara_agentic
-Version: 0.1.8
+Version: 0.1.9
 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: llama-index-tools-arxiv==0.2.0
 Requires-Dist: llama-index-tools-database==0.2.0
 Requires-Dist: llama-index-tools-google==0.2.0
 Requires-Dist: llama-index-tools-tavily_research==0.2.0
+Requires-Dist: llama-index-callbacks-arize-phoenix==0.2.1
 Requires-Dist: pydantic==2.8.2
 Requires-Dist: retrying==1.3.4
 Requires-Dist: pymongo==4.6.1
@@ -63,7 +64,7 @@ Requires-Dist: tiktoken==0.7.0
 - [Vectara account](https://console.vectara.com/signup/?utm_source=github&utm_medium=code&utm_term=DevRel&utm_content=vectara-agentic&utm_campaign=github-code-DevRel-vectara-agentic)
 - A Vectara corpus with an [API key](https://docs.vectara.com/docs/api-keys)
 - [Python 3.10 or higher](https://www.python.org/downloads/)
-- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere, or GROQ)
+- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere or GROQ)
 
 ## Installation
 
@@ -181,6 +182,25 @@ The `Agent` class defines a few helpful methods to help you understand the inter
 * The `report()` method prints out the agent object’s type, the tools, and the LLMs used for the main agent and tool calling.
 * The `token_counts()` method tells you how many tokens you have used in the current session for both the main agent and tool calling LLMs. This can be helpful if you want to track spend by token.
 
+## Observability
+
+vectara-agentic supports observability via the existing integration of LlamaIndex and Arize Phoenix.
+To enable tracing of your vectara-agentic assistant, follow these steps (adapted from [here](https://docs.llamaindex.ai/en/stable/module_guides/observability/)):
+1. Go to `https://llamatrace.com/login` an create an account, then create an API key and put it in the `PHOENIX_API_KEY` variable
+2. `os["VECTARA_AGENTIC_OBSERVER_TYPE"] = "ARIZE_PHOENIX"`: to enable Arize Phoenix observability
+3. `os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"api_key={PHOENIX_API_KEY}"`
+
+Now when you run your agent, all metrics are sent to LlamaTrace and recorded. You can view them at `https://llamatrace.com`.
+If you do not include the `OTEL_EXPORTER_OTLP_HEADERS` a local instance of Arize Phoenix will be setup instead and you can view it at `http://localhost:6006`
+
+## About Custom Instructions
+
+The custom instructions you provide to the agent guide its behavior.
+Here are some guidelines when creating your instructions:
+- Write precise and clear instructions, without overcomplicating.
+- Consider edge cases and unusual or atypical scenarios.
+- Be cautious to not over-specify behavior based on your primary use-case, as it may limit the agent's ability to behave properly in others.
+
 ## Examples
 
 Check out our example AI assistants:

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/README.md

@@ -24,7 +24,7 @@
 - [Vectara account](https://console.vectara.com/signup/?utm_source=github&utm_medium=code&utm_term=DevRel&utm_content=vectara-agentic&utm_campaign=github-code-DevRel-vectara-agentic)
 - A Vectara corpus with an [API key](https://docs.vectara.com/docs/api-keys)
 - [Python 3.10 or higher](https://www.python.org/downloads/)
-- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere, or GROQ)
+- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere or GROQ)
 
 ## Installation
 
@@ -142,6 +142,25 @@ The `Agent` class defines a few helpful methods to help you understand the inter
 * The `report()` method prints out the agent object’s type, the tools, and the LLMs used for the main agent and tool calling.
 * The `token_counts()` method tells you how many tokens you have used in the current session for both the main agent and tool calling LLMs. This can be helpful if you want to track spend by token.
 
+## Observability
+
+vectara-agentic supports observability via the existing integration of LlamaIndex and Arize Phoenix.
+To enable tracing of your vectara-agentic assistant, follow these steps (adapted from [here](https://docs.llamaindex.ai/en/stable/module_guides/observability/)):
+1. Go to `https://llamatrace.com/login` an create an account, then create an API key and put it in the `PHOENIX_API_KEY` variable
+2. `os["VECTARA_AGENTIC_OBSERVER_TYPE"] = "ARIZE_PHOENIX"`: to enable Arize Phoenix observability
+3. `os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"api_key={PHOENIX_API_KEY}"`
+
+Now when you run your agent, all metrics are sent to LlamaTrace and recorded. You can view them at `https://llamatrace.com`.
+If you do not include the `OTEL_EXPORTER_OTLP_HEADERS` a local instance of Arize Phoenix will be setup instead and you can view it at `http://localhost:6006`
+
+## About Custom Instructions
+
+The custom instructions you provide to the agent guide its behavior.
+Here are some guidelines when creating your instructions:
+- Write precise and clear instructions, without overcomplicating.
+- Consider edge cases and unusual or atypical scenarios.
+- Be cautious to not over-specify behavior based on your primary use-case, as it may limit the agent's ability to behave properly in others.
+
 ## Examples
 
 Check out our example AI assistants:

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/requirements.txt

@@ -13,6 +13,7 @@ llama-index-tools-arxiv==0.2.0
 llama-index-tools-database==0.2.0
 llama-index-tools-google==0.2.0
 llama-index-tools-tavily_research==0.2.0
+llama-index-callbacks-arize-phoenix==0.2.1
 pydantic==2.8.2
 retrying==1.3.4
 pymongo==4.6.1

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/setup.py

@@ -8,7 +8,7 @@ def read_requirements():
 
 setup(
     name="vectara_agentic",
-    version="0.1.8",
+    version="0.1.9",
     author="Ofer Mendelevitch",
     author_email="ofer@vectara.com",
     description="A Python package for creating AI Assistants and AI Agents with Vectara",

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/vectara_agentic/__init__.py

@@ -3,7 +3,7 @@ vectara_agentic package.
 """
 
 # Define the package version
-__version__ = "0.1.8"
+__version__ = "0.1.9"
 
 # Import classes and functions from modules
 # from .module1 import Class1, function1

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/vectara_agentic/_prompts.py

@@ -88,16 +88,17 @@ If this format is used, the user will respond in the following format:
 Observation: tool response
 ```
 
-You should keep repeating the above format till you have enough information to answer the question without using any more tools. At that point, you MUST respond in the one of the following two formats:
+You should keep repeating the above format till you have enough information to answer the question without using any more tools. 
+At that point, you MUST respond in the one of the following two formats (and do not include any Action):
 
 ```
 Thought: I can answer without using any more tools. I'll use the user's language to answer
-Answer: [your answer here (In the same language as the user's question)]
+Answer: [your answer here (In the same language as the user's question, and maintain any references/citations)]
 ```
 
 ```
 Thought: I cannot answer the question with the provided tools.
-Answer: [your answer here (In the same language as the user's question)]
+Answer: [your answer here (In the same language as the user's question, and maintain any references/citations)]
 ```
 
 ## Current Conversation

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/vectara_agentic/agent.py

@@ -1,16 +1,18 @@
 """
 This module contains the Agent class for handling different types of agents and their interactions.
 """
-
 from typing import List, Callable, Optional
 import os
 from datetime import date
 import time
 
+import logging
+logger = logging.getLogger('opentelemetry.exporter.otlp.proto.http.trace_exporter')
+logger.setLevel(logging.CRITICAL)
+
 from retrying import retry
 from pydantic import Field, create_model
 
-
 from llama_index.core.tools import FunctionTool
 from llama_index.core.agent import ReActAgent
 from llama_index.core.agent.react.formatter import ReActChatFormatter
@@ -21,6 +23,7 @@ from llama_index.agent.openai import OpenAIAgent
 from llama_index.core.memory import ChatMemoryBuffer
 from llama_index.core import set_global_handler
 
+import phoenix as px
 
 from dotenv import load_dotenv
 
@@ -113,7 +116,7 @@ class Agent:
                 memory=memory,
                 verbose=verbose,
                 react_chat_formatter=ReActChatFormatter(system_header=prompt),
-                max_iterations=20,
+                max_iterations=30,
                 callable_manager=callback_manager,
             )
         elif self.agent_type == AgentType.OPENAI:
@@ -124,7 +127,7 @@ class Agent:
                 memory=memory,
                 verbose=verbose,
                 callable_manager=callback_manager,
-                max_function_calls=10,
+                max_function_calls=20,
                 system_prompt=prompt,
             )
         elif self.agent_type == AgentType.LLMCOMPILER:
@@ -139,8 +142,13 @@ class Agent:
 
         observer = ObserverType(os.getenv("VECTARA_AGENTIC_OBSERVER_TYPE", "NO_OBSERVER"))
         if observer == ObserverType.ARIZE_PHOENIX:
-            set_global_handler("arize_phoenix", endpoint="https://llamatrace.com/v1/traces")
-            print("Arize Phoenix observer set.")
+            if os.environ.get("OTEL_EXPORTER_OTLP_HEADERS", None):
+                set_global_handler("arize_phoenix", endpoint="https://llamatrace.com/v1/traces")
+                print("Arize Phoenix observer set. https://llamatrace.com")
+            else:
+                px.launch_app()
+                set_global_handler("arize_phoenix", endpoint="http://localhost:6006/v1/traces")
+                print("Arize Phoenix observer set. http://localhost:6006/.")
         else:
             print("No observer set.")
 
@@ -174,11 +182,11 @@ class Agent:
     def from_corpus(
         cls,
         tool_name: str,
-        vectara_customer_id: str,
-        vectara_corpus_id: str,
-        vectara_api_key: str,
         data_description: str,
         assistant_specialty: str,
+        vectara_customer_id: str = str(os.environ.get("VECTARA_CUSTOMER_ID", "")),
+        vectara_corpus_id: str = str(os.environ.get("VECTARA_CORPUS_ID", "")),
+        vectara_api_key: str = str(os.environ.get("VECTARA_API_KEY", "")),
         verbose: bool = False,
         vectara_filter_fields: list[dict] = [],
         vectara_lambda_val: float = 0.005,

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/vectara_agentic/tools.py

@@ -5,6 +5,7 @@ This module contains the ToolsFactory class for creating agent tools.
 import inspect
 import re
 import importlib
+import os
 
 from typing import Callable, List, Any, Optional, Type
 from pydantic import BaseModel, Field
@@ -94,9 +95,9 @@ class VectaraToolFactory:
 
     def __init__(
         self,
-        vectara_customer_id: str,
-        vectara_corpus_id: str,
-        vectara_api_key: str,
+        vectara_customer_id: str = str(os.environ.get("VECTARA_CUSTOMER_ID", "")),
+        vectara_corpus_id: str = str(os.environ.get("VECTARA_CORPUS_ID", "")),
+        vectara_api_key: str = str(os.environ.get("VECTARA_API_KEY", "")),
     ) -> None:
         """
         Initialize the VectaraToolFactory
@@ -154,6 +155,7 @@ class VectaraToolFactory:
             vectara_api_key=self.vectara_api_key,
             vectara_customer_id=self.vectara_customer_id,
             vectara_corpus_id=self.vectara_corpus_id,
+            x_source_str="vectara-agentic"
         )
 
         def _build_filter_string(kwargs):
@@ -233,17 +235,18 @@ class VectaraToolFactory:
                     raw_output={'response': msg}
                 )
                 
-
             res = {
                 "response": response.response,
                 "references_metadata": citation_metadata,
             }
-
-            tool_output = f"""
-                Response: '''{res['response']}'''
-                References:
-                {res['references_metadata']}
-            """
+            if len(citation_metadata) > 0:
+                tool_output = f"""
+                    Response: '''{res['response']}'''
+                    References:
+                    {res['references_metadata']}
+                """
+            else:
+                tool_output = f"Response: '''{res['response']}'''"
             out = ToolOutput(
                 tool_name=rag_function.__name__,
                 content=tool_output,

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9/vectara_agentic.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectara_agentic
-Version: 0.1.8
+Version: 0.1.9
 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: llama-index-tools-arxiv==0.2.0
 Requires-Dist: llama-index-tools-database==0.2.0
 Requires-Dist: llama-index-tools-google==0.2.0
 Requires-Dist: llama-index-tools-tavily_research==0.2.0
+Requires-Dist: llama-index-callbacks-arize-phoenix==0.2.1
 Requires-Dist: pydantic==2.8.2
 Requires-Dist: retrying==1.3.4
 Requires-Dist: pymongo==4.6.1
@@ -63,7 +64,7 @@ Requires-Dist: tiktoken==0.7.0
 - [Vectara account](https://console.vectara.com/signup/?utm_source=github&utm_medium=code&utm_term=DevRel&utm_content=vectara-agentic&utm_campaign=github-code-DevRel-vectara-agentic)
 - A Vectara corpus with an [API key](https://docs.vectara.com/docs/api-keys)
 - [Python 3.10 or higher](https://www.python.org/downloads/)
-- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere, or GROQ)
+- OpenAI API key (or API keys for Anthropic, TOGETHER.AI, Fireworks AI, Cohere or GROQ)
 
 ## Installation
 
@@ -181,6 +182,25 @@ The `Agent` class defines a few helpful methods to help you understand the inter
 * The `report()` method prints out the agent object’s type, the tools, and the LLMs used for the main agent and tool calling.
 * The `token_counts()` method tells you how many tokens you have used in the current session for both the main agent and tool calling LLMs. This can be helpful if you want to track spend by token.
 
+## Observability
+
+vectara-agentic supports observability via the existing integration of LlamaIndex and Arize Phoenix.
+To enable tracing of your vectara-agentic assistant, follow these steps (adapted from [here](https://docs.llamaindex.ai/en/stable/module_guides/observability/)):
+1. Go to `https://llamatrace.com/login` an create an account, then create an API key and put it in the `PHOENIX_API_KEY` variable
+2. `os["VECTARA_AGENTIC_OBSERVER_TYPE"] = "ARIZE_PHOENIX"`: to enable Arize Phoenix observability
+3. `os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"api_key={PHOENIX_API_KEY}"`
+
+Now when you run your agent, all metrics are sent to LlamaTrace and recorded. You can view them at `https://llamatrace.com`.
+If you do not include the `OTEL_EXPORTER_OTLP_HEADERS` a local instance of Arize Phoenix will be setup instead and you can view it at `http://localhost:6006`
+
+## About Custom Instructions
+
+The custom instructions you provide to the agent guide its behavior.
+Here are some guidelines when creating your instructions:
+- Write precise and clear instructions, without overcomplicating.
+- Consider edge cases and unusual or atypical scenarios.
+- Be cautious to not over-specify behavior based on your primary use-case, as it may limit the agent's ability to behave properly in others.
+
 ## Examples
 
 Check out our example AI assistants:

{vectara_agentic-0.1.8 → vectara_agentic-0.1.9}/vectara_agentic.egg-info/requires.txt

@@ -13,6 +13,7 @@ llama-index-tools-arxiv==0.2.0
 llama-index-tools-database==0.2.0
 llama-index-tools-google==0.2.0
 llama-index-tools-tavily_research==0.2.0
+llama-index-callbacks-arize-phoenix==0.2.1
 pydantic==2.8.2
 retrying==1.3.4
 pymongo==4.6.1