vectara-agentic 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

vectara_agentic/types.py

@@ -18,8 +18,6 @@ class AgentType(Enum):
 
     REACT = "REACT"
     FUNCTION_CALLING = "FUNCTION_CALLING"
-    LLMCOMPILER = "LLMCOMPILER"
-    LATS = "LATS"
 
 
 class ObserverType(Enum):
@@ -142,8 +140,16 @@ class AgentStreamingResponse:
             resp = cast(AgentResponse, self.base.get_response())
         elif hasattr(self.base, "to_response"):
             resp = cast(AgentResponse, self.base.to_response())
-        else:
+        elif hasattr(self.base, "get_final_response"):
             resp = cast(AgentResponse, self.base.get_final_response())
+        else:
+            # Fallback for StreamingAgentChatResponse objects that don't have standard methods
+            # Try to get the response directly from the object's response attribute
+            if hasattr(self.base, "response"):
+                response_text = self.base.response if isinstance(self.base.response, str) else str(self.base.response)
+                resp = AgentResponse(response=response_text, metadata=getattr(self.base, "metadata", {}))
+            else:
+                resp = AgentResponse(response="", metadata={})
 
         resp.metadata = (resp.metadata or {}) | self.metadata
         return resp

{vectara_agentic-0.4.0.dist-info → vectara_agentic-0.4.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.4.0
+Version: 0.4.1
 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 +16,11 @@ 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==0.12.52
+Requires-Dist: llama-index-core==0.12.52.post1
 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
@@ -53,7 +51,7 @@ Requires-Dist: openinference-instrumentation-llama-index==4.3.1
 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: pandas==2.2.3
@@ -125,7 +123,7 @@ 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 +530,49 @@ 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:
@@ -745,7 +786,7 @@ 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.

vectara_agentic-0.4.1.dist-info/RECORD

@@ -0,0 +1,53 @@
+tests/__init__.py,sha256=vXhQJCyD1Uhx2NP8b8vIUG3RUhkXyvn7oOir2bmctQU,175
+tests/conftest.py,sha256=PlHevWpkOP1F9pG9GJSf8ewYW_1FsFYcx3CQyjxAziY,9286
+tests/endpoint.py,sha256=0URgtz8uydhP_rtpGn_59P1LiWkd3idNlI85LzXnlUE,2744
+tests/run_tests.py,sha256=2dKDJ2uhz6SKlr72Zkh7PTVb2F52_FpirM_wKiIFuiw,3232
+tests/test_agent.py,sha256=dwCHul-GnpURAmSMJlNo9_k_Aizr4KhkJKccKwDvZ38,5778
+tests/test_agent_fallback_memory.py,sha256=1LoRHxUM767bGmCeusPlGubX_pIeP5KxIABRwdWLJGo,10862
+tests/test_agent_memory_consistency.py,sha256=D8ivCGp5reJyOK7Q6wDiZlv3bKX4-SEchnqocyib1Po,8966
+tests/test_agent_type.py,sha256=d5Zs0iM12DxregfwkJ6UxERWcR5eLgy2ona1znwvK3I,5153
+tests/test_api_endpoint.py,sha256=I2UDamPMSLLkgw0pZ5QMM0o_8vVga9-F6ql-S3zlMBs,5136
+tests/test_bedrock.py,sha256=74M4k4MWFfZV-mD75R_27HQGTfWcPQ40ijLanT54y-E,1979
+tests/test_fallback.py,sha256=6wkyiyAvsibIdr33aXdsuU9nzDeJt0XSz5yiyuisUEQ,2963
+tests/test_gemini.py,sha256=pvCcfTf79-R49H_WVZou1xx-vVmZEY-19zRtxZeUdD4,2581
+tests/test_groq.py,sha256=OmO-VBrKfZYUc11QfZH25jT3FySQrSpv_FS488IqSik,1970
+tests/test_private_llm.py,sha256=P6sldeAWcHg29u_Nu4FdHVUyNaRe5ULE-hjNJz6WKHc,2620
+tests/test_return_direct.py,sha256=QsCw-ZGp06cutLkyrLh1U1rggoH7iBiFz4SQ9MIx-Xk,1521
+tests/test_serialization.py,sha256=wdVRoy6hoPqCF7SGpYbC2TM7iR2o_IKIRKOBZFAChp0,4824
+tests/test_session_memory.py,sha256=hnADl59agjpXySY-CBjw6sDPn3s6JketIK6XbLZsLzU,9691
+tests/test_streaming.py,sha256=EBihBb_ZQiGCCvv7Us7YqHN4CxDIQy-XsUSDVO1n5wU,3302
+tests/test_together.py,sha256=s0ywOxL-XT_iq970ucamVAPR_CIS9OT72vJB7degNdc,1983
+tests/test_tools.py,sha256=869Fl54kmLc44ijykO2QpfcXyAWLDqJ9Niq3XNzhzv8,13621
+tests/test_vectara_llms.py,sha256=H1M9OaDvD8_GCFRBm6IdvWejYKn-zm3-Rzt_noCBbiQ,2496
+tests/test_vhc.py,sha256=MXyFxckQzfdXcULqwoao4taoQ93qLDvkcf-h2LwUQnE,1974
+tests/test_workflow.py,sha256=dwQnHSxvRMVqUtFV8O2KvuyaSKJXFDkVhcffn8mSuJs,3555
+vectara_agentic/__init__.py,sha256=CfS3QR4drKygcTcyH5zUUDuXXQ3WZtTCytz8W4-loeE,1077
+vectara_agentic/_callback.py,sha256=ueckIfLNa9ykmmEyLqrrZwfDNWrEfyZzJeWktpnkwJQ,12970
+vectara_agentic/_observability.py,sha256=c_1WuP8rS9sPuMH6twzcz6CGLqfTT5y4fyOHvDVdxsg,4423
+vectara_agentic/_version.py,sha256=dWTo8m6tq_yNZLAER4W8gWnDQib4KBI28u8pwf8jiRM,65
+vectara_agentic/agent.py,sha256=2laHGTp1D2ve96zdxdN3wtq0MMIe5B8RxTxDXrJDTOE,46779
+vectara_agentic/agent_config.py,sha256=njqEX2qHJjAp2KpNuJglgZhyWXPK74wjIjBPACD6w7w,4074
+vectara_agentic/agent_endpoint.py,sha256=E_AF-YwxaKqd1-p43X62e1e4ugwOWKIyNq4RWOfsO7A,7402
+vectara_agentic/db_tools.py,sha256=nVZkpGdG63ooGngjX9g7YWyBZRtYMDpvzNasbO696nM,11498
+vectara_agentic/llm_utils.py,sha256=dgomwK7FOVmH_prgOR60CjhG6kwt-AxxMLlFa8vWspY,7449
+vectara_agentic/sub_query_workflow.py,sha256=wm2Lb2wbKrYx5bSq-npb3XbaxWzTcvK5BkW3NZ9vuIc,12968
+vectara_agentic/tool_utils.py,sha256=whnQlk9coeIt01sqUnKnzUorefgn96yWqhtRfHxNL84,25921
+vectara_agentic/tools.py,sha256=8gmC6UnHFTUr_hWWbuMyRNMMLkeY5Sb1FTgCsb7Hx1w,35689
+vectara_agentic/tools_catalog.py,sha256=p6eRram-diJyMz5dZI703auSAm97FfW5wLAMyz_2sB0,4634
+vectara_agentic/types.py,sha256=qKkK8vRNiLvEcMInMyOClK2bD7iFlrWGTkl3fGC6Xic,6117
+vectara_agentic/utils.py,sha256=R9HitEG5K3Q_p2M_teosT181OUxkhs1-hnj98qDYGbE,2545
+vectara_agentic/agent_core/__init__.py,sha256=R3KGbSOiY21FOjbeQ_GyIi6uR9Rz7PTfudO9RjSuEZQ,722
+vectara_agentic/agent_core/factory.py,sha256=AMlUuAwUVocqwfOYkW-HJuUr81Kj0kUjcG4pPXmCZMM,14201
+vectara_agentic/agent_core/prompts.py,sha256=HJ8b-5OEn6-suqWqQgeAVOZNEiPr7wKHeaczNdL-XN8,10127
+vectara_agentic/agent_core/serialization.py,sha256=Ag9Ux497_IyxrexYP90wbG-UJy-lTH1ec_ANmpPmQjo,11731
+vectara_agentic/agent_core/streaming.py,sha256=Xzz0kgt1LFeKlnhlDTsZmBze-asvYauwIlYJi2hgHjk,17772
+vectara_agentic/agent_core/utils/__init__.py,sha256=y5Xf0IH-5TRxMBRA9IyhmWnGZOVIyqV45P6lX4c2Qsc,762
+vectara_agentic/agent_core/utils/hallucination.py,sha256=XmV7tW-MBN9BrzM79zu0T7zaWil7fIkNQjLfDZE43v4,5312
+vectara_agentic/agent_core/utils/logging.py,sha256=-Ll8iUelml92WuhNWScuY6H-RheyZOTBHNxXQ1UGy0M,1701
+vectara_agentic/agent_core/utils/schemas.py,sha256=e7xhJBevgK7IM8cRT5hoO67T-Ep_FhNGp72Zo0OC_Jo,2853
+vectara_agentic/agent_core/utils/tools.py,sha256=k9Gm-UUQ3ZeGxrkjyrjmjcGxOkvnpylcm_Krnr-0fsY,4748
+vectara_agentic-0.4.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vectara_agentic-0.4.1.dist-info/METADATA,sha256=PuM3HoXyagcOndjlq7XM5gPAGkjntAgIxI72OkHCLhw,35059
+vectara_agentic-0.4.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+vectara_agentic-0.4.1.dist-info/top_level.txt,sha256=Y7TQTFdOYGYodQRltUGRieZKIYuzeZj2kHqAUpfCUfg,22
+vectara_agentic-0.4.1.dist-info/RECORD,,

vectara_agentic/agent_core/utils/prompt_formatting.py

@@ -1,56 +0,0 @@
-"""
-Prompt formatting and templating utilities.
-
-This module handles prompt template processing, placeholder replacement,
-and LLM-specific prompt formatting for different agent types.
-"""
-
-from datetime import date
-
-def format_prompt(
-    prompt_template: str,
-    general_instructions: str,
-    topic: str,
-    custom_instructions: str,
-) -> str:
-    """
-    Generate a prompt by replacing placeholders with topic and date.
-
-    Args:
-        prompt_template: The template for the prompt
-        general_instructions: General instructions to be included in the prompt
-        topic: The topic to be included in the prompt
-        custom_instructions: The custom instructions to be included in the prompt
-
-    Returns:
-        str: The formatted prompt
-    """
-    return (
-        prompt_template.replace("{chat_topic}", topic)
-        .replace("{today}", date.today().strftime("%A, %B %d, %Y"))
-        .replace("{custom_instructions}", custom_instructions)
-        .replace("{INSTRUCTIONS}", general_instructions)
-    )
-
-
-def format_llm_compiler_prompt(
-    prompt: str, general_instructions: str, topic: str, custom_instructions: str
-) -> str:
-    """
-    Add custom instructions to the prompt for LLM compiler agents.
-
-    Args:
-        prompt: The base prompt to which custom instructions should be added
-        general_instructions: General instructions for the agent
-        topic: Topic expertise for the agent
-        custom_instructions: Custom user instructions
-
-    Returns:
-        str: The prompt with custom instructions added
-    """
-    prompt += "\nAdditional Instructions:\n"
-    prompt += f"You have expertise in {topic}.\n"
-    prompt += general_instructions
-    prompt += custom_instructions
-    prompt += f"Today is {date.today().strftime('%A, %B %d, %Y')}"
-    return prompt

vectara_agentic-0.4.0.dist-info/RECORD

@@ -1,50 +0,0 @@
-tests/__init__.py,sha256=vXhQJCyD1Uhx2NP8b8vIUG3RUhkXyvn7oOir2bmctQU,175
-tests/conftest.py,sha256=WHK_SxlhU2EN55w8wXUMMHhks8yriOab5nK1y8HXe3g,9276
-tests/endpoint.py,sha256=0URgtz8uydhP_rtpGn_59P1LiWkd3idNlI85LzXnlUE,2744
-tests/run_tests.py,sha256=eZd50pV4FIbr8riDaqXvDheoW3mOcO3ZRGloGUNusAM,3197
-tests/test_agent.py,sha256=V5r7Cqe0iqV8VmeDJdE2lvB5tBLQUqcX182HIXTNYQQ,5721
-tests/test_agent_type.py,sha256=WNUwyUxC431BTtQPSfKpG42IxsPnexdbXQTM3P6itBk,5085
-tests/test_api_endpoint.py,sha256=I2UDamPMSLLkgw0pZ5QMM0o_8vVga9-F6ql-S3zlMBs,5136
-tests/test_bedrock.py,sha256=lXIHGtH0otjOqCkCSnanEUM6HavSkbail1900drfJiU,1358
-tests/test_fallback.py,sha256=6wkyiyAvsibIdr33aXdsuU9nzDeJt0XSz5yiyuisUEQ,2963
-tests/test_gemini.py,sha256=ksHd8JA7ZMuzs8W40Fb4RBoen1rniXDghSfQImw_3nk,3016
-tests/test_groq.py,sha256=m6HpJEeqmDQqYCQwg9_bCyGJ3ek1tK-aLBktxgRGGJ0,1346
-tests/test_private_llm.py,sha256=P6sldeAWcHg29u_Nu4FdHVUyNaRe5ULE-hjNJz6WKHc,2620
-tests/test_return_direct.py,sha256=QsCw-ZGp06cutLkyrLh1U1rggoH7iBiFz4SQ9MIx-Xk,1521
-tests/test_serialization.py,sha256=CsW7qEXgGE24oEqo85c-GEbzn_mZjbF3er_juL9JbF8,4896
-tests/test_streaming.py,sha256=e_XztBLCWf39HgfN1zsUz_vFNblzmMC2zfYHB8JM-zQ,2795
-tests/test_tools.py,sha256=869Fl54kmLc44ijykO2QpfcXyAWLDqJ9Niq3XNzhzv8,13621
-tests/test_vectara_llms.py,sha256=H1M9OaDvD8_GCFRBm6IdvWejYKn-zm3-Rzt_noCBbiQ,2496
-tests/test_vhc.py,sha256=oDZzx1AdtDO0K5MHpzrCegw7wfc3h9E0V7boVFoMWXs,1945
-tests/test_workflow.py,sha256=FXUM4hKh-La9FRJD0ir2sOiXsvkDFe2kI0r1faRAlMc,3873
-vectara_agentic/__init__.py,sha256=CfS3QR4drKygcTcyH5zUUDuXXQ3WZtTCytz8W4-loeE,1077
-vectara_agentic/_callback.py,sha256=ueckIfLNa9ykmmEyLqrrZwfDNWrEfyZzJeWktpnkwJQ,12970
-vectara_agentic/_observability.py,sha256=c_1WuP8rS9sPuMH6twzcz6CGLqfTT5y4fyOHvDVdxsg,4423
-vectara_agentic/_version.py,sha256=tSVqctgqLCPSvb0zkh8BNhEaR1d92yEJqmdCvwJzdKQ,65
-vectara_agentic/agent.py,sha256=ga-8Flc01EX6xUhEx-MHArjb8bUeAYlRK_cKioihxdk,38667
-vectara_agentic/agent_config.py,sha256=njqEX2qHJjAp2KpNuJglgZhyWXPK74wjIjBPACD6w7w,4074
-vectara_agentic/agent_endpoint.py,sha256=E_AF-YwxaKqd1-p43X62e1e4ugwOWKIyNq4RWOfsO7A,7402
-vectara_agentic/db_tools.py,sha256=nVZkpGdG63ooGngjX9g7YWyBZRtYMDpvzNasbO696nM,11498
-vectara_agentic/llm_utils.py,sha256=s0g04lqQkX27njAKPAM-H0ZFEmohaC0VO7hs_ByaGaQ,7460
-vectara_agentic/sub_query_workflow.py,sha256=wm2Lb2wbKrYx5bSq-npb3XbaxWzTcvK5BkW3NZ9vuIc,12968
-vectara_agentic/tool_utils.py,sha256=whnQlk9coeIt01sqUnKnzUorefgn96yWqhtRfHxNL84,25921
-vectara_agentic/tools.py,sha256=8gmC6UnHFTUr_hWWbuMyRNMMLkeY5Sb1FTgCsb7Hx1w,35689
-vectara_agentic/tools_catalog.py,sha256=p6eRram-diJyMz5dZI703auSAm97FfW5wLAMyz_2sB0,4634
-vectara_agentic/types.py,sha256=V04L8Man79qI9SmnKhlR3verJjm7yhcEE1RHPq9ADpc,5580
-vectara_agentic/utils.py,sha256=R9HitEG5K3Q_p2M_teosT181OUxkhs1-hnj98qDYGbE,2545
-vectara_agentic/agent_core/__init__.py,sha256=R3KGbSOiY21FOjbeQ_GyIi6uR9Rz7PTfudO9RjSuEZQ,722
-vectara_agentic/agent_core/factory.py,sha256=yIoA-GumyuoUu-tmfAp79v2kAujUj7D7a7d5vx3_kj8,17697
-vectara_agentic/agent_core/prompts.py,sha256=JGyAyZyLd__hTuEeBBuCHFdIS1nTIQJZJPGbxRpxY7A,9414
-vectara_agentic/agent_core/serialization.py,sha256=Kxa7irtaeOhw2NbPpPkT3R7rKe-imx13XCL1V63eRqI,11634
-vectara_agentic/agent_core/streaming.py,sha256=0mN5qpDP9evXOG_vj65GINhmUkbSQsWmGUsVDkNVPFE,18134
-vectara_agentic/agent_core/utils/__init__.py,sha256=kLdT0Idw0xhT1zOJIhx13T4qsWh01O3taNC7aN2SEI4,958
-vectara_agentic/agent_core/utils/hallucination.py,sha256=KG-ELY9ZzCwBjj4KMyncPkgvEg190Pw2D612O9fHE-Q,7037
-vectara_agentic/agent_core/utils/logging.py,sha256=-Ll8iUelml92WuhNWScuY6H-RheyZOTBHNxXQ1UGy0M,1701
-vectara_agentic/agent_core/utils/prompt_formatting.py,sha256=C0WqmSHZ-r_asRi2mkMsFOlqrOVrmADqNudidS6CU3s,1801
-vectara_agentic/agent_core/utils/schemas.py,sha256=e7xhJBevgK7IM8cRT5hoO67T-Ep_FhNGp72Zo0OC_Jo,2853
-vectara_agentic/agent_core/utils/tools.py,sha256=k9Gm-UUQ3ZeGxrkjyrjmjcGxOkvnpylcm_Krnr-0fsY,4748
-vectara_agentic-0.4.0.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vectara_agentic-0.4.0.dist-info/METADATA,sha256=BAILIhLZFOZAo71UTsWlzDPnUGfmq8nhJDRfAwzEgEc,33857
-vectara_agentic-0.4.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-vectara_agentic-0.4.0.dist-info/top_level.txt,sha256=Y7TQTFdOYGYodQRltUGRieZKIYuzeZj2kHqAUpfCUfg,22
-vectara_agentic-0.4.0.dist-info/RECORD,,