vectara-agentic 0.2.13__py3-none-any.whl → 0.2.14__py3-none-any.whl

vectara_agentic/utils.py

@@ -2,164 +2,11 @@
 Utilities for the Vectara agentic.
 """
 
-from typing import Tuple, Callable, Optional
-from functools import lru_cache
 from inspect import signature
 import json
 import asyncio
-import tiktoken
 import aiohttp
 
-from llama_index.core.llms import LLM
-from llama_index.llms.openai import OpenAI
-from llama_index.llms.anthropic import Anthropic
-
-from .types import LLMRole, AgentType, ModelProvider
-from .agent_config import AgentConfig
-
-provider_to_default_model_name = {
-    ModelProvider.OPENAI: "gpt-4o",
-    ModelProvider.ANTHROPIC: "claude-3-7-sonnet-latest",
-    ModelProvider.TOGETHER: "Qwen/Qwen2.5-72B-Instruct-Turbo",
-    ModelProvider.GROQ: "meta-llama/llama-4-scout-17b-16e-instruct",
-    ModelProvider.FIREWORKS: "accounts/fireworks/models/firefunction-v2",
-    ModelProvider.BEDROCK: "anthropic.claude-3-7-sonnet-20250219-v1:0",
-    ModelProvider.COHERE: "command-a-03-2025",
-    ModelProvider.GEMINI: "models/gemini-2.0-flash",
-}
-
-DEFAULT_MODEL_PROVIDER = ModelProvider.OPENAI
-
-
-@lru_cache(maxsize=None)
-def _get_llm_params_for_role(
-    role: LLMRole, config: Optional[AgentConfig] = None
-) -> Tuple[ModelProvider, str]:
-    """
-    Get the model provider and model name for the specified role.
-
-    If config is None, a new AgentConfig() is instantiated using environment defaults.
-    """
-    config = config or AgentConfig()  # fallback to default config
-
-    if role == LLMRole.TOOL:
-        model_provider = ModelProvider(config.tool_llm_provider)
-        # If the user hasn’t explicitly set a tool_llm_model_name,
-        # fallback to provider default from provider_to_default_model_name
-        model_name = config.tool_llm_model_name or provider_to_default_model_name.get(
-            model_provider
-        )
-    else:
-        model_provider = ModelProvider(config.main_llm_provider)
-        model_name = config.main_llm_model_name or provider_to_default_model_name.get(
-            model_provider
-        )
-
-    # If the agent type is OpenAI, check that the main LLM provider is also OpenAI.
-    if role == LLMRole.MAIN and config.agent_type == AgentType.OPENAI:
-        if model_provider != ModelProvider.OPENAI:
-            raise ValueError(
-                "OpenAI agent requested but main model provider is not OpenAI."
-            )
-
-    return model_provider, model_name
-
-
-@lru_cache(maxsize=None)
-def get_tokenizer_for_model(
-    role: LLMRole, config: Optional[AgentConfig] = None
-) -> Optional[Callable]:
-    """
-    Get the tokenizer for the specified model, as determined by the role & config.
-    """
-    model_provider, model_name = _get_llm_params_for_role(role, config)
-    if model_provider == ModelProvider.OPENAI:
-        # This might raise an exception if the model_name is unknown to tiktoken
-        return tiktoken.encoding_for_model(model_name).encode
-    if model_provider == ModelProvider.ANTHROPIC:
-        return Anthropic().tokenizer
-    return None
-
-
-@lru_cache(maxsize=None)
-def get_llm(role: LLMRole, config: Optional[AgentConfig] = None) -> LLM:
-    """
-    Get the LLM for the specified role, using the provided config
-    or a default if none is provided.
-    """
-    max_tokens = 8192
-    model_provider, model_name = _get_llm_params_for_role(role, config)
-    if model_provider == ModelProvider.OPENAI:
-        llm = OpenAI(
-            model=model_name,
-            temperature=0,
-            is_function_calling_model=True,
-            strict=True,
-            max_tokens=max_tokens,
-            pydantic_program_mode="openai",
-        )
-    elif model_provider == ModelProvider.ANTHROPIC:
-        llm = Anthropic(
-            model=model_name,
-            temperature=0,
-            max_tokens=max_tokens,
-        )
-    elif model_provider == ModelProvider.GEMINI:
-        from llama_index.llms.gemini import Gemini
-
-        llm = Gemini(
-            model=model_name,
-            temperature=0,
-            is_function_calling_model=True,
-            allow_parallel_tool_calls=True,
-            max_tokens=max_tokens,
-        )
-    elif model_provider == ModelProvider.TOGETHER:
-        from llama_index.llms.together import TogetherLLM
-
-        llm = TogetherLLM(
-            model=model_name,
-            temperature=0,
-            is_function_calling_model=True,
-            max_tokens=max_tokens,
-        )
-    elif model_provider == ModelProvider.GROQ:
-        from llama_index.llms.groq import Groq
-
-        llm = Groq(
-            model=model_name,
-            temperature=0,
-            is_function_calling_model=True,
-            max_tokens=max_tokens,
-        )
-    elif model_provider == ModelProvider.FIREWORKS:
-        from llama_index.llms.fireworks import Fireworks
-
-        llm = Fireworks(model=model_name, temperature=0, max_tokens=max_tokens)
-    elif model_provider == ModelProvider.BEDROCK:
-        from llama_index.llms.bedrock import Bedrock
-
-        llm = Bedrock(model=model_name, temperature=0, max_tokens=max_tokens)
-    elif model_provider == ModelProvider.COHERE:
-        from llama_index.llms.cohere import Cohere
-
-        llm = Cohere(model=model_name, temperature=0, max_tokens=max_tokens)
-    elif model_provider == ModelProvider.PRIVATE:
-        from llama_index.llms.openai_like import OpenAILike
-
-        llm = OpenAILike(
-            model=model_name,
-            temperature=0,
-            is_function_calling_model=True,
-            is_chat_model=True,
-            api_base=config.private_llm_api_base,
-            api_key=config.private_llm_api_key,
-            max_tokens=max_tokens,
-        )
-    else:
-        raise ValueError(f"Unknown LLM provider: {model_provider}")
-    return llm
-
 
 def is_float(value: str) -> bool:
     """Check if a string can be converted to a float."""

{vectara_agentic-0.2.13.dist-info → vectara_agentic-0.2.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectara_agentic
-Version: 0.2.13
+Version: 0.2.14
 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
@@ -16,18 +16,18 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llama-index==0.12.31
-Requires-Dist: llama-index-indices-managed-vectara==0.4.3
+Requires-Dist: llama-index==0.12.33
+Requires-Dist: llama-index-indices-managed-vectara==0.4.4
 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==0.3.35
+Requires-Dist: llama-index-llms-openai==0.3.38
 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==0.4.1
-Requires-Dist: llama-index-llms-gemini==0.4.14
+Requires-Dist: llama-index-llms-google-genai==0.1.8
 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
@@ -49,7 +49,7 @@ Requires-Dist: arize-phoenix==8.26.1
 Requires-Dist: arize-phoenix-otel==0.9.2
 Requires-Dist: protobuf==5.29.3
 Requires-Dist: tokenizers>=0.20
-Requires-Dist: pydantic==2.10.6
+Requires-Dist: pydantic==2.11.3
 Requires-Dist: retrying==1.3.4
 Requires-Dist: python-dotenv==1.0.1
 Requires-Dist: tiktoken==0.9.0
@@ -292,13 +292,12 @@ For example, in the quickstart example the schema is:
 
 ```python
 class QueryFinancialReportsArgs(BaseModel):
-    query: str = Field(..., description="The user query.")
     year: int | str = Field(..., description=f"The year this query relates to. An integer between {min(years)} and {max(years)} or a string specifying a condition on the year (example: '>2020').")
     ticker: str = Field(..., description=f"The company ticker. Must be a valid ticket symbol from the list {tickers.keys()}.")
 ```
 
-The `query` is required and is always the query string.
-The other arguments are optional and will be interpreted as Vectara metadata filters.
+Remember, the `query` argument is part of the rag_tool that is generated, but `vectara-agentic` creates it and you do 
+not need to specify it explicitly. 
 
 For example, in the example above, the agent may call the `query_financial_reports_tool` tool with 
 query='what is the revenue?', year=2022 and ticker='AAPL'. Subsequently the RAG tool will issue
@@ -483,13 +482,28 @@ class MyWorkflow(Workflow):
         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:
+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`
 
+If you want to use `agent`, `tools`, `llm` or `verbose` in other events (that are not `StartEvent`), you can store them in
+the `Context` of the Workflow as follows:
+
+```python
+await ctx.set("agent", ev.agent)
+```
+
+and then in any other event you can pull that agent object with
+
+```python
+agent = await ctx.get("agent")
+```
+
+Similarly you can reuse the `llm`, `tools` or `verbose` arguments within other nodes in the workflow.
+
 ### Using the Workflow with Your Agent
 
 When initializing your agent, pass the workflow class using the `workflow_cls` parameter:
@@ -521,7 +535,7 @@ print(workflow_result.answer)
 
 ### Built-in Workflows
 
-`vectara-agentic` includes two powerful workflow implementations that you can use right away:
+`vectara-agentic` includes two workflow implementations that you can use right away:
 
 #### 1. `SubQuestionQueryWorkflow`
 

{vectara_agentic-0.2.13.dist-info → vectara_agentic-0.2.14.dist-info}/RECORD

@@ -4,27 +4,30 @@ tests/test_agent.py,sha256=nkg3SefST9Q-38Ys9yLJZr2RN6FxeXonMGj7uRCsta8,5482
 tests/test_agent_planning.py,sha256=r_Qk63aK6gAzIluv3X6CLCNIbE1ExWJEUIkvoI6U7RE,2213
 tests/test_agent_type.py,sha256=mWo-pTQNDj4fWFPETm5jnb7Y5N48aW35keTVvxdIaCc,7173
 tests/test_fallback.py,sha256=M5YD7NHZ0joVU1frYIr9_OiRAIje5mrXrYVcekzlyGs,2829
+tests/test_groq.py,sha256=0FFnQ91o9UjOIAIe_JMxyBl4dz_38RRbl00j9dFudMs,4170
 tests/test_private_llm.py,sha256=CY-_rCpxGUuxnZ3ypkodw5Jj-sJCNdh6rLbCvULwuJI,2247
 tests/test_serialization.py,sha256=Ed23GN2zhSJNdPFrVK4aqLkOhJKviczR_o0t-r9TuRI,4762
-tests/test_tools.py,sha256=2W-NIb-wG3_MIKOK8PLpnmQvxaQM-rLFucXYdbNcZeI,10499
-tests/test_vectara_llms.py,sha256=TGiE-56FEcUVxTfzGT-zfb3RSNlAuPCZqHAeeJienVo,2714
+tests/test_tools.py,sha256=b90pbLHEqjbtfiCVDOsYCwUCJXTEE-jIu5WuA8r6Yg8,11920
+tests/test_vectara_llms.py,sha256=wpDFOuExoUqRwqH7Ikhb8mVmkq1e85m2p1fMMFF2_GE,2298
 tests/test_workflow.py,sha256=lVyrVHdRO5leYNbYtHTmKqMX0c8_xehCpUA7cXQKVsc,2175
 vectara_agentic/__init__.py,sha256=2GLDS3U6KckK-dBRl9v_x1kSV507gEhjOfuMmmu0Qxg,850
 vectara_agentic/_callback.py,sha256=ron49t1t-ox-736WaXzrZ99vhN4NI9bMiHFyj0iIPqg,13062
 vectara_agentic/_observability.py,sha256=BA2zhwa5930aaDUJxHefPlmIPt8kZOuLHVBc9PtYNuU,3839
 vectara_agentic/_prompts.py,sha256=8d5gaaY_OrNVDlGqb7cqIZq0WnK5RY7yVa8LgHDjbhA,9508
-vectara_agentic/_version.py,sha256=ek7TRbAOgDn0gZnwy8aFjdMPr2VxLMyx77_v_7d7T0A,66
-vectara_agentic/agent.py,sha256=sJq4IrpqKGiqFXSYCRuQ3mbxUH6uoLEI93I_-q8TM7c,47635
+vectara_agentic/_version.py,sha256=yDIvGWQ2X4m-Tnp9W4synsKkQknhptDZf8ZdOLb-NJ8,66
+vectara_agentic/agent.py,sha256=v6LdfDckGtcUomxiTsIsslBqJCW2eOApEwK67f6AWVw,50283
 vectara_agentic/agent_config.py,sha256=E-rtYMcpoGxnEAyy8231bizo2n0uGQ2qWxuSgTEfwdQ,4327
 vectara_agentic/agent_endpoint.py,sha256=QIMejCLlpW2qzXxeDAxv3anF46XMDdVMdKGWhJh3azY,1996
 vectara_agentic/db_tools.py,sha256=bAgqQMrpmu7KBaiAjJ4tpH8JwsFGEDk8iru5Deu0SEk,11179
+vectara_agentic/llm_utils.py,sha256=Isf1d9K4Jpn-IwMZn-liPUTEF-bpiqp0XIiNRohtwTQ,6152
 vectara_agentic/sub_query_workflow.py,sha256=xjySd2qjLAKwK6XuS0R0PTyk2uXraHCgCbDP1xDoFVI,12175
-vectara_agentic/tools.py,sha256=uC4O4wvC1oSDjQlyNf-YhNK0I_C4wOzZT-AaQJnxhgA,48458
-vectara_agentic/tools_catalog.py,sha256=oiw3wAfbpFhh0_6rMvZsyPqWV6QIzHqhZCNzqRxuyV8,4818
+vectara_agentic/tool_utils.py,sha256=e3hSOblo5voDfY8tmNdKS9UCeq1jt24BMLPKuHB2UgE,18056
+vectara_agentic/tools.py,sha256=qg103AizNYO1p7i_ZZGFwkmJj5FNdtHB4cgcvcxwDIE,32387
+vectara_agentic/tools_catalog.py,sha256=s0tjmXAp-0wttRKy5QpWhYFBW-D6KNWbcARWLYVdEVo,4840
 vectara_agentic/types.py,sha256=HcS7vR8P2v2xQTlOc6ZFV2vvlr3OpzSNWhtcLMxqUZc,1792
-vectara_agentic/utils.py,sha256=0M-3bvuFP2xcUPxxLdq-cQsbi4AOSWavtv0FH4SaYJs,8006
-vectara_agentic-0.2.13.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vectara_agentic-0.2.13.dist-info/METADATA,sha256=kc8N1NsVIKZjqyyitLI7EmvWXMYcUbeDyNehziQU0bs,27734
-vectara_agentic-0.2.13.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
-vectara_agentic-0.2.13.dist-info/top_level.txt,sha256=Y7TQTFdOYGYodQRltUGRieZKIYuzeZj2kHqAUpfCUfg,22
-vectara_agentic-0.2.13.dist-info/RECORD,,
+vectara_agentic/utils.py,sha256=q14S8nm3UFFI3ksk-xszd9xgFrtXdIt_tdRiBMFjaa0,2529
+vectara_agentic-0.2.14.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vectara_agentic-0.2.14.dist-info/METADATA,sha256=agfZoMDE5zechuOTmlEiK-NLudqxDRKAdIvp2ngryOw,28114
+vectara_agentic-0.2.14.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+vectara_agentic-0.2.14.dist-info/top_level.txt,sha256=Y7TQTFdOYGYodQRltUGRieZKIYuzeZj2kHqAUpfCUfg,22
+vectara_agentic-0.2.14.dist-info/RECORD,,

{vectara_agentic-0.2.13.dist-info → vectara_agentic-0.2.14.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any