vectara-agentic 0.4.0__tar.gz → 0.4.2__tar.gz

{vectara_agentic-0.4.0/vectara_agentic.egg-info → vectara_agentic-0.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.4.0
+Version: 0.4.2
 Summary: A Python package for creating AI Assistants and AI Agents with Vectara
 Home-page: https://github.com/vectara/py-vectara-agentic
 Author: Ofer Mendelevitch
@@ -16,46 +16,43 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.49
-Requires-Dist: llama-index-core==0.12.49
+Requires-Dist: llama-index==0.13.1
+Requires-Dist: llama-index-core==0.13.1
 Requires-Dist: llama-index-workflow==1.0.1
-Requires-Dist: llama-index-cli==0.4.4
-Requires-Dist: llama-index-indices-managed-vectara==0.4.5
-Requires-Dist: llama-index-agent-llm-compiler==0.3.2
-Requires-Dist: llama-index-agent-lats==0.3.2
-Requires-Dist: llama-index-agent-openai==0.4.12
-Requires-Dist: llama-index-llms-openai==0.4.7
-Requires-Dist: llama-index-llms-openai-like==0.4.0
-Requires-Dist: llama-index-llms-anthropic==0.7.6
-Requires-Dist: llama-index-llms-together==0.3.2
-Requires-Dist: llama-index-llms-groq==0.3.2
-Requires-Dist: llama-index-llms-cohere==0.5.0
-Requires-Dist: llama-index-llms-google-genai==0.2.5
-Requires-Dist: llama-index-llms-bedrock-converse==0.7.6
-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==0.5.0
-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==0.3.1
-Requires-Dist: llama-index-tools-bing-search==0.3.0
-Requires-Dist: openai>=1.96.1
-Requires-Dist: tavily-python>=0.7.9
-Requires-Dist: exa-py>=1.14.8
-Requires-Dist: openinference-instrumentation-llama-index==4.3.1
+Requires-Dist: llama-index-cli==0.5.0
+Requires-Dist: llama-index-indices-managed-vectara==0.5.0
+Requires-Dist: llama-index-llms-openai==0.5.2
+Requires-Dist: llama-index-llms-openai-like==0.5.0
+Requires-Dist: llama-index-llms-anthropic==0.8.2
+Requires-Dist: llama-index-llms-together==0.4.0
+Requires-Dist: llama-index-llms-groq==0.4.0
+Requires-Dist: llama-index-llms-cohere==0.6.0
+Requires-Dist: llama-index-llms-google-genai==0.3.0
+Requires-Dist: llama-index-llms-bedrock-converse==0.8.0
+Requires-Dist: llama-index-tools-yahoo-finance==0.4.0
+Requires-Dist: llama-index-tools-arxiv==0.4.0
+Requires-Dist: llama-index-tools-database==0.4.0
+Requires-Dist: llama-index-tools-google==0.6.0
+Requires-Dist: llama-index-tools-tavily_research==0.4.0
+Requires-Dist: llama_index.tools.brave_search==0.4.0
+Requires-Dist: llama-index-tools-neo4j==0.4.0
+Requires-Dist: llama-index-tools-waii==0.4.0
+Requires-Dist: llama-index-graph-stores-kuzu==0.9.0
+Requires-Dist: llama-index-tools-salesforce==0.4.0
+Requires-Dist: llama-index-tools-slack==0.4.0
+Requires-Dist: llama-index-tools-exa==0.4.0
+Requires-Dist: llama-index-tools-wikipedia==0.4.0
+Requires-Dist: llama-index-tools-bing-search==0.4.0
+Requires-Dist: openai>=1.99.3
+Requires-Dist: tavily-python>=0.7.10
+Requires-Dist: exa-py>=1.14.20
+Requires-Dist: openinference-instrumentation-llama-index==4.3.4
 Requires-Dist: opentelemetry-proto>=1.31.0
 Requires-Dist: arize-phoenix==10.9.1
 Requires-Dist: arize-phoenix-otel==0.10.3
-Requires-Dist: protobuf==5.29.3
+Requires-Dist: protobuf==5.29.5
 Requires-Dist: tokenizers>=0.20
-Requires-Dist: pydantic==2.11.5
+Requires-Dist: pydantic>=2.11.5
 Requires-Dist: pandas==2.2.3
 Requires-Dist: retrying==1.3.4
 Requires-Dist: python-dotenv==1.0.1
@@ -125,7 +122,7 @@ Dynamic: summary
 - **Rapid Tool Creation:**  
   Build Vectara RAG tools or search tools with a single line of code.
 - **Agent Flexibility:**  
-  Supports multiple agent types including `ReAct`, `Function Calling`, `LATS`, and `LLMCompiler`.
+  Supports multiple agent types including `ReAct` and `Function Calling`.
 - **Pre-Built Domain Tools:**  
   Tools tailored for finance, legal, and other verticals.
 - **Multi-LLM Integration:**  
@@ -532,6 +529,49 @@ Built-in formatters include `format_as_table`, `format_as_json`, and `format_as_
 
 The human-readable format, if available, is used when using Vectara Hallucination Correction.
 
+## 🔍 Vectara Hallucination Correction (VHC)
+
+`vectara-agentic` provides built-in support for Vectara Hallucination Correction (VHC), which analyzes agent responses and corrects any detected hallucinations based on the factual content retrieved by VHC-eligible tools.
+
+### Computing VHC
+
+After a chat interaction, you can compute VHC to analyze and correct the agent's response:
+
+```python
+# Chat with the agent
+response = agent.chat("What was Apple's revenue in 2022?")
+print(response.response)
+
+# Compute VHC analysis
+vhc_result = agent.compute_vhc()
+
+# Access corrected text and corrections
+if vhc_result["corrected_text"]:
+    print("Original:", response.response)
+    print("Corrected:", vhc_result["corrected_text"])
+    print("Corrections:", vhc_result["corrections"])
+else:
+    print("No corrections needed or VHC not available")
+```
+
+### Async VHC Computation
+
+For async applications, use `acompute_vhc()`:
+
+```python
+# Async chat
+response = await agent.achat("What was Apple's revenue in 2022?")
+
+# Async VHC computation
+vhc_result = await agent.acompute_vhc()
+```
+
+### VHC Requirements
+
+- VHC requires a valid `VECTARA_API_KEY` environment variable
+- Only VHC-eligible tools (those marked with `vhc_eligible=True`) contribute to the analysis
+- VHC results are cached for each query/response pair to avoid redundant computation
+
 ### Tool Validation
 
 When creating an agent, you can enable tool validation by setting `validate_tools=True`. This will check that any tools mentioned in your custom instructions actually exist in the agent's tool set:
@@ -745,11 +785,11 @@ agent = Agent(
 ```
 
 The `AgentConfig` object may include the following items:
-- `agent_type`: the agent type. Valid values are `REACT`, `LLMCOMPILER`, `LATS` or `FUNCTION_CALLING` (default: `FUNCTION_CALLING`).
+- `agent_type`: the agent type. Valid values are `REACT` or `FUNCTION_CALLING` (default: `FUNCTION_CALLING`).
 - `main_llm_provider` and `tool_llm_provider`: the LLM provider for main agent and for the tools. Valid values are `OPENAI`, `ANTHROPIC`, `TOGETHER`, `GROQ`, `COHERE`, `BEDROCK`, `GEMINI` (default: `OPENAI`).
 
 > **Note:** Fireworks AI support has been removed. If you were using Fireworks, please migrate to one of the supported providers listed above.
-- `main_llm_model_name` and `tool_llm_model_name`: agent model name for agent and tools (default depends on provider: OpenAI uses gpt-4.1, Gemini uses gemini-2.5-flash).
+- `main_llm_model_name` and `tool_llm_model_name`: agent model name for agent and tools (default depends on provider: OpenAI uses gpt-4.1-mini, Gemini uses gemini-2.5-flash).
 - `observer`: the observer type; should be `ARIZE_PHOENIX` or if undefined no observation framework will be used.
 - `endpoint_api_key`: a secret key if using the API endpoint option (defaults to `dev-api-key`)
 

{vectara_agentic-0.4.0 → vectara_agentic-0.4.2}/README.md

@@ -48,7 +48,7 @@
 - **Rapid Tool Creation:**  
   Build Vectara RAG tools or search tools with a single line of code.
 - **Agent Flexibility:**  
-  Supports multiple agent types including `ReAct`, `Function Calling`, `LATS`, and `LLMCompiler`.
+  Supports multiple agent types including `ReAct` and `Function Calling`.
 - **Pre-Built Domain Tools:**  
   Tools tailored for finance, legal, and other verticals.
 - **Multi-LLM Integration:**  
@@ -455,6 +455,49 @@ Built-in formatters include `format_as_table`, `format_as_json`, and `format_as_
 
 The human-readable format, if available, is used when using Vectara Hallucination Correction.
 
+## 🔍 Vectara Hallucination Correction (VHC)
+
+`vectara-agentic` provides built-in support for Vectara Hallucination Correction (VHC), which analyzes agent responses and corrects any detected hallucinations based on the factual content retrieved by VHC-eligible tools.
+
+### Computing VHC
+
+After a chat interaction, you can compute VHC to analyze and correct the agent's response:
+
+```python
+# Chat with the agent
+response = agent.chat("What was Apple's revenue in 2022?")
+print(response.response)
+
+# Compute VHC analysis
+vhc_result = agent.compute_vhc()
+
+# Access corrected text and corrections
+if vhc_result["corrected_text"]:
+    print("Original:", response.response)
+    print("Corrected:", vhc_result["corrected_text"])
+    print("Corrections:", vhc_result["corrections"])
+else:
+    print("No corrections needed or VHC not available")
+```
+
+### Async VHC Computation
+
+For async applications, use `acompute_vhc()`:
+
+```python
+# Async chat
+response = await agent.achat("What was Apple's revenue in 2022?")
+
+# Async VHC computation
+vhc_result = await agent.acompute_vhc()
+```
+
+### VHC Requirements
+
+- VHC requires a valid `VECTARA_API_KEY` environment variable
+- Only VHC-eligible tools (those marked with `vhc_eligible=True`) contribute to the analysis
+- VHC results are cached for each query/response pair to avoid redundant computation
+
 ### Tool Validation
 
 When creating an agent, you can enable tool validation by setting `validate_tools=True`. This will check that any tools mentioned in your custom instructions actually exist in the agent's tool set:
@@ -668,11 +711,11 @@ agent = Agent(
 ```
 
 The `AgentConfig` object may include the following items:
-- `agent_type`: the agent type. Valid values are `REACT`, `LLMCOMPILER`, `LATS` or `FUNCTION_CALLING` (default: `FUNCTION_CALLING`).
+- `agent_type`: the agent type. Valid values are `REACT` or `FUNCTION_CALLING` (default: `FUNCTION_CALLING`).
 - `main_llm_provider` and `tool_llm_provider`: the LLM provider for main agent and for the tools. Valid values are `OPENAI`, `ANTHROPIC`, `TOGETHER`, `GROQ`, `COHERE`, `BEDROCK`, `GEMINI` (default: `OPENAI`).
 
 > **Note:** Fireworks AI support has been removed. If you were using Fireworks, please migrate to one of the supported providers listed above.
-- `main_llm_model_name` and `tool_llm_model_name`: agent model name for agent and tools (default depends on provider: OpenAI uses gpt-4.1, Gemini uses gemini-2.5-flash).
+- `main_llm_model_name` and `tool_llm_model_name`: agent model name for agent and tools (default depends on provider: OpenAI uses gpt-4.1-mini, Gemini uses gemini-2.5-flash).
 - `observer`: the observer type; should be `ARIZE_PHOENIX` or if undefined no observation framework will be used.
 - `endpoint_api_key`: a secret key if using the API endpoint option (defaults to `dev-api-key`)
 

vectara_agentic-0.4.2/requirements.txt

@@ -0,0 +1,43 @@
+llama-index==0.13.1
+llama-index-core==0.13.1
+llama-index-workflow==1.0.1
+llama-index-cli==0.5.0
+llama-index-indices-managed-vectara==0.5.0
+llama-index-llms-openai==0.5.2
+llama-index-llms-openai-like==0.5.0
+llama-index-llms-anthropic==0.8.2
+llama-index-llms-together==0.4.0
+llama-index-llms-groq==0.4.0
+llama-index-llms-cohere==0.6.0
+llama-index-llms-google-genai==0.3.0
+llama-index-llms-bedrock-converse==0.8.0
+llama-index-tools-yahoo-finance==0.4.0
+llama-index-tools-arxiv==0.4.0
+llama-index-tools-database==0.4.0
+llama-index-tools-google==0.6.0
+llama-index-tools-tavily_research==0.4.0
+llama_index.tools.brave_search==0.4.0
+llama-index-tools-neo4j==0.4.0
+llama-index-tools-waii==0.4.0
+llama-index-graph-stores-kuzu==0.9.0
+llama-index-tools-salesforce==0.4.0
+llama-index-tools-slack==0.4.0
+llama-index-tools-exa==0.4.0
+llama-index-tools-wikipedia==0.4.0
+llama-index-tools-bing-search==0.4.0
+openai>=1.99.3
+tavily-python>=0.7.10
+exa-py>=1.14.20
+openinference-instrumentation-llama-index==4.3.4
+opentelemetry-proto>=1.31.0
+arize-phoenix==10.9.1
+arize-phoenix-otel==0.10.3
+protobuf==5.29.5
+tokenizers>=0.20
+pydantic>=2.11.5
+pandas==2.2.3
+retrying==1.3.4
+python-dotenv==1.0.1
+cloudpickle>=3.1.1
+httpx==0.28.1
+commonmark==0.9.1