diff --git a/docs/concepts/flows.mdx b/docs/concepts/flows.mdx index 324118310..cf9d20f63 100644 --- a/docs/concepts/flows.mdx +++ b/docs/concepts/flows.mdx @@ -138,7 +138,7 @@ print("---- Final Output ----") print(final_output) ```` -``` text Output +```text Output ---- Final Output ---- Second method received: Output from first_method ```` diff --git a/docs/concepts/knowledge.mdx b/docs/concepts/knowledge.mdx index 8a777833e..ba4f54450 100644 --- a/docs/concepts/knowledge.mdx +++ b/docs/concepts/knowledge.mdx @@ -4,8 +4,6 @@ description: What is knowledge in CrewAI and how to use it. icon: book --- -# Using Knowledge in CrewAI - ## What is Knowledge? Knowledge in CrewAI is a powerful system that allows AI agents to access and utilize external information sources during their tasks. @@ -36,7 +34,20 @@ CrewAI supports various types of knowledge sources out of the box: -## Quick Start +## Supported Knowledge Parameters + +| Parameter | Type | Required | Description | +| :--------------------------- | :---------------------------------- | :------- | :---------------------------------------------------------------------------------------------------------------------------------------------------- | +| `sources` | **List[BaseKnowledgeSource]** | Yes | List of knowledge sources that provide content to be stored and queried. Can include PDF, CSV, Excel, JSON, text files, or string content. | +| `collection_name` | **str** | No | Name of the collection where the knowledge will be stored. Used to identify different sets of knowledge. Defaults to "knowledge" if not provided. | +| `storage` | **Optional[KnowledgeStorage]** | No | Custom storage configuration for managing how the knowledge is stored and retrieved. If not provided, a default storage will be created. | + +## Quickstart Example + + +For file-Based Knowledge Sources, make sure to place your files in a `knowledge` directory at the root of your project. +Also, use relative paths from the `knowledge` directory when creating the source. + Here's an example using string-based knowledge: @@ -80,7 +91,8 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o ``` -Here's another example with the `CrewDoclingSource` +Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including TXT, PDF, DOCX, HTML, and more. + ```python Code from crewai import LLM, Agent, Crew, Process, Task from crewai.knowledge.source.crew_docling_source import CrewDoclingSource @@ -128,39 +140,192 @@ result = crew.kickoff( ) ``` +## More Examples + +Here are examples of how to use different types of knowledge sources: + +### Text File Knowledge Source +```python +from crewai.knowledge.source import CrewDoclingSource + +# Create a text file knowledge source +text_source = CrewDoclingSource( + file_paths=["document.txt", "another.txt"] +) + +# Create knowledge with text file source +knowledge = Knowledge( + collection_name="text_knowledge", + sources=[text_source] +) +``` + +### PDF Knowledge Source +```python +from crewai.knowledge.source import PDFKnowledgeSource + +# Create a PDF knowledge source +pdf_source = PDFKnowledgeSource( + file_paths=["document.pdf", "another.pdf"] +) + +# Create knowledge with PDF source +knowledge = Knowledge( + collection_name="pdf_knowledge", + sources=[pdf_source] +) +``` + +### CSV Knowledge Source +```python +from crewai.knowledge.source import CSVKnowledgeSource + +# Create a CSV knowledge source +csv_source = CSVKnowledgeSource( + file_paths=["data.csv"] +) + +# Create knowledge with CSV source +knowledge = Knowledge( + collection_name="csv_knowledge", + sources=[csv_source] +) +``` + +### Excel Knowledge Source +```python +from crewai.knowledge.source import ExcelKnowledgeSource + +# Create an Excel knowledge source +excel_source = ExcelKnowledgeSource( + file_paths=["spreadsheet.xlsx"] +) + +# Create knowledge with Excel source +knowledge = Knowledge( + collection_name="excel_knowledge", + sources=[excel_source] +) +``` + +### JSON Knowledge Source +```python +from crewai.knowledge.source import JSONKnowledgeSource + +# Create a JSON knowledge source +json_source = JSONKnowledgeSource( + file_paths=["data.json"] +) + +# Create knowledge with JSON source +knowledge = Knowledge( + collection_name="json_knowledge", + sources=[json_source] +) +``` + ## Knowledge Configuration ### Chunking Configuration -Control how content is split for processing by setting the chunk size and overlap. +Knowledge sources automatically chunk content for better processing. +You can configure chunking behavior in your knowledge sources: -```python Code -knowledge_source = StringKnowledgeSource( - content="Long content...", - chunk_size=4000, # Characters per chunk (default) - chunk_overlap=200 # Overlap between chunks (default) +```python +from crewai.knowledge.source import StringKnowledgeSource + +source = StringKnowledgeSource( + content="Your content here", + chunk_size=4000, # Maximum size of each chunk (default: 4000) + chunk_overlap=200 # Overlap between chunks (default: 200) ) ``` -## Embedder Configuration +The chunking configuration helps in: +- Breaking down large documents into manageable pieces +- Maintaining context through chunk overlap +- Optimizing retrieval accuracy -You can also configure the embedder for the knowledge store. This is useful if you want to use a different embedder for the knowledge store than the one used for the agents. +### Embeddings Configuration -```python Code -... +You can also configure the embedder for the knowledge store. +This is useful if you want to use a different embedder for the knowledge store than the one used for the agents. +The `embedder` parameter supports various embedding model providers that include: +- `openai`: OpenAI's embedding models +- `google`: Google's text embedding models +- `azure`: Azure OpenAI embeddings +- `ollama`: Local embeddings with Ollama +- `vertexai`: Google Cloud VertexAI embeddings +- `cohere`: Cohere's embedding models +- `bedrock`: AWS Bedrock embeddings +- `huggingface`: Hugging Face models +- `watson`: IBM Watson embeddings + +Here's an example of how to configure the embedder for the knowledge store using Google's `text-embedding-004` model: + +```python Example +from crewai import Agent, Task, Crew, Process, LLM +from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource +import os + +# Get the GEMINI API key +GEMINI_API_KEY = os.environ.get("GEMINI_API_KEY") + +# Create a knowledge source +content = "Users name is John. He is 30 years old and lives in San Francisco." string_source = StringKnowledgeSource( - content="Users name is John. He is 30 years old and lives in San Francisco.", + content=content, ) + +# Create an LLM with a temperature of 0 to ensure deterministic outputs +gemini_llm = LLM( + model="gemini/gemini-1.5-pro-002", + api_key=GEMINI_API_KEY, + temperature=0, +) + +# Create an agent with the knowledge store +agent = Agent( + role="About User", + goal="You know everything about the user.", + backstory="""You are a master at understanding people and their preferences.""", + verbose=True, + allow_delegation=False, + llm=gemini_llm, +) + +task = Task( + description="Answer the following questions about the user: {question}", + expected_output="An answer to the question.", + agent=agent, +) + crew = Crew( - ... + agents=[agent], + tasks=[task], + verbose=True, + process=Process.sequential, knowledge_sources=[string_source], embedder={ - "provider": "openai", - "config": {"model": "text-embedding-3-small"}, - }, + "provider": "google", + "config": { + "model": "models/text-embedding-004", + "api_key": GEMINI_API_KEY, + } + } ) -``` +result = crew.kickoff(inputs={"question": "What city does John live in and how old is he?"}) +``` +```text Output +# Agent: About User +## Task: Answer the following questions about the user: What city does John live in and how old is he? + +# Agent: About User +## Final Answer: +John is 30 years old and lives in San Francisco. +``` + ## Clearing Knowledge If you need to clear the knowledge stored in CrewAI, you can use the `crewai reset-memories` command with the `--knowledge` option. diff --git a/docs/how-to/Portkey-Observability-and-Guardrails.md b/docs/how-to/portkey-observability-and-guardrails.mdx similarity index 100% rename from docs/how-to/Portkey-Observability-and-Guardrails.md rename to docs/how-to/portkey-observability-and-guardrails.mdx diff --git a/docs/how-to/portkey-observability.mdx b/docs/how-to/portkey-observability.mdx new file mode 100644 index 000000000..4002323a5 --- /dev/null +++ b/docs/how-to/portkey-observability.mdx @@ -0,0 +1,202 @@ +--- +title: Portkey Observability and Guardrails +description: How to use Portkey with CrewAI +icon: key +--- + +Portkey CrewAI Header Image + + +[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast. + +Portkey adds 4 core production capabilities to any CrewAI agent: +1. Routing to **200+ LLMs** +2. Making each LLM call more robust +3. Full-stack tracing & cost, performance analytics +4. Real-time guardrails to enforce behavior + +## Getting Started + + + + ```bash + pip install -qU crewai portkey-ai + ``` + + + To build CrewAI Agents with Portkey, you'll need two keys: + - **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key + - **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault + + ```python + from crewai import LLM + from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL + + gpt_llm = LLM( + model="gpt-4", + base_url=PORTKEY_GATEWAY_URL, + api_key="dummy", # We are using Virtual key + extra_headers=createHeaders( + api_key="YOUR_PORTKEY_API_KEY", + virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey + ) + ) + ``` + + + ```python + from crewai import Agent, Task, Crew + + # Define your agents with roles and goals + coder = Agent( + role='Software developer', + goal='Write clear, concise code on demand', + backstory='An expert coder with a keen eye for software trends.', + llm=gpt_llm + ) + + # Create tasks for your agents + task1 = Task( + description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!", + expected_output="A clear and concise HTML code", + agent=coder + ) + + # Instantiate your crew + crew = Crew( + agents=[coder], + tasks=[task1], + ) + + result = crew.kickoff() + print(result) + ``` + + + +## Key Features + +| Feature | Description | +|:--------|:------------| +| ๐ŸŒ Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface | +| ๐Ÿ›ก๏ธ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks | +| ๐Ÿ“Š Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata | +| ๐Ÿ” Comprehensive Logging | Debug with detailed execution traces and function call logs | +| ๐Ÿšง Security Controls | Set budget limits and implement role-based access control | +| ๐Ÿ”„ Performance Analytics | Capture and analyze feedback for continuous improvement | +| ๐Ÿ’พ Intelligent Caching | Reduce costs and latency with semantic or simple caching | + + +## Production Features with Portkey Configs + +All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference. + + + + + + +### 1. Use 250+ LLMs +Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api) + + +Easily switch between different LLM providers: + +```python +# Anthropic Configuration +anthropic_llm = LLM( + model="claude-3-5-sonnet-latest", + base_url=PORTKEY_GATEWAY_URL, + api_key="dummy", + extra_headers=createHeaders( + api_key="YOUR_PORTKEY_API_KEY", + virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys + trace_id="anthropic_agent" + ) +) + +# Azure OpenAI Configuration +azure_llm = LLM( + model="gpt-4", + base_url=PORTKEY_GATEWAY_URL, + api_key="dummy", + extra_headers=createHeaders( + api_key="YOUR_PORTKEY_API_KEY", + virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys + trace_id="azure_agent" + ) +) +``` + + +### 2. Caching +Improve response times and reduce costs with two powerful caching modes: +- **Simple Cache**: Perfect for exact matches +- **Semantic Cache**: Matches responses for requests that are semantically similar +[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic) + +```py +config = { + "cache": { + "mode": "semantic", # or "simple" for exact matching + } +} +``` + +### 3. Production Reliability +Portkey provides comprehensive reliability features: +- **Automatic Retries**: Handle temporary failures gracefully +- **Request Timeouts**: Prevent hanging operations +- **Conditional Routing**: Route requests based on specific conditions +- **Fallbacks**: Set up automatic provider failovers +- **Load Balancing**: Distribute requests efficiently + +[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/) + + + +### 4. Metrics + +Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need. + + +- Cost per agent interaction +- Response times and latency +- Token usage and efficiency +- Success/failure rates +- Cache hit rates + +Portkey Dashboard + +### 5. Detailed Logging +Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes. + + +Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata. + +
+ Traces + Portkey Traces +
+ +
+ Logs + Portkey Logs +
+ +### 6. Enterprise Security Features +- Set budget limit and rate limts per Virtual Key (disposable API keys) +- Implement role-based access control +- Track system changes with audit logs +- Configure data retention policies + + + +For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs). + +## Resources + +- [๐Ÿ“˜ Portkey Documentation](https://docs.portkey.ai) +- [๐Ÿ“Š Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) +- [๐Ÿฆ Twitter](https://twitter.com/portkeyai) +- [๐Ÿ’ฌ Discord Community](https://discord.gg/DD7vgKK299) diff --git a/docs/mint.json b/docs/mint.json index fad9689b8..9103434b4 100644 --- a/docs/mint.json +++ b/docs/mint.json @@ -100,7 +100,8 @@ "how-to/conditional-tasks", "how-to/agentops-observability", "how-to/langtrace-observability", - "how-to/openlit-observability" + "how-to/openlit-observability", + "how-to/portkey-observability" ] }, { diff --git a/src/crewai/crew.py b/src/crewai/crew.py index d488783ea..c01a89280 100644 --- a/src/crewai/crew.py +++ b/src/crewai/crew.py @@ -726,11 +726,7 @@ class Crew(BaseModel): # Determine which tools to use - task tools take precedence over agent tools tools_for_task = task.tools or agent_to_use.tools or [] - tools_for_task = self._prepare_tools( - agent_to_use, - task, - tools_for_task - ) + tools_for_task = self._prepare_tools(agent_to_use, task, tools_for_task) self._log_task_start(task, agent_to_use.role) @@ -797,14 +793,18 @@ class Crew(BaseModel): return skipped_task_output return None - def _prepare_tools(self, agent: BaseAgent, task: Task, tools: List[Tool]) -> List[Tool]: + def _prepare_tools( + self, agent: BaseAgent, task: Task, tools: List[Tool] + ) -> List[Tool]: # Add delegation tools if agent allows delegation if agent.allow_delegation: if self.process == Process.hierarchical: if self.manager_agent: tools = self._update_manager_tools(task, tools) else: - raise ValueError("Manager agent is required for hierarchical process.") + raise ValueError( + "Manager agent is required for hierarchical process." + ) elif agent and agent.allow_delegation: tools = self._add_delegation_tools(task, tools) @@ -823,7 +823,9 @@ class Crew(BaseModel): return self.manager_agent return task.agent - def _merge_tools(self, existing_tools: List[Tool], new_tools: List[Tool]) -> List[Tool]: + def _merge_tools( + self, existing_tools: List[Tool], new_tools: List[Tool] + ) -> List[Tool]: """Merge new tools into existing tools list, avoiding duplicates by tool name.""" if not new_tools: return existing_tools @@ -839,7 +841,9 @@ class Crew(BaseModel): return tools - def _inject_delegation_tools(self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent]): + def _inject_delegation_tools( + self, tools: List[Tool], task_agent: BaseAgent, agents: List[BaseAgent] + ): delegation_tools = task_agent.get_delegation_tools(agents) return self._merge_tools(tools, delegation_tools) @@ -856,7 +860,9 @@ class Crew(BaseModel): if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent: if not tools: tools = [] - tools = self._inject_delegation_tools(tools, task.agent, agents_for_delegation) + tools = self._inject_delegation_tools( + tools, task.agent, agents_for_delegation + ) return tools def _log_task_start(self, task: Task, role: str = "None"): @@ -870,7 +876,9 @@ class Crew(BaseModel): if task.agent: tools = self._inject_delegation_tools(tools, task.agent, [task.agent]) else: - tools = self._inject_delegation_tools(tools, self.manager_agent, self.agents) + tools = self._inject_delegation_tools( + tools, self.manager_agent, self.agents + ) return tools def _get_context(self, task: Task, task_outputs: List[TaskOutput]): diff --git a/src/crewai/llm.py b/src/crewai/llm.py index 5d6a0ccf5..bdac7080a 100644 --- a/src/crewai/llm.py +++ b/src/crewai/llm.py @@ -6,8 +6,10 @@ import warnings from contextlib import contextmanager from typing import Any, Dict, List, Optional, Union -import litellm -from litellm import get_supported_openai_params +with warnings.catch_warnings(): + warnings.simplefilter("ignore", UserWarning) + import litellm + from litellm import get_supported_openai_params from crewai.utilities.exceptions.context_window_exceeding_exception import ( LLMContextLengthExceededException, @@ -138,7 +140,7 @@ class LLM: self.kwargs = kwargs litellm.drop_params = True - litellm.set_verbose = False + self.set_callbacks(callbacks) self.set_env_callbacks() diff --git a/src/crewai/utilities/internal_instructor.py b/src/crewai/utilities/internal_instructor.py index 13fe5a19f..a3206ba15 100644 --- a/src/crewai/utilities/internal_instructor.py +++ b/src/crewai/utilities/internal_instructor.py @@ -1,3 +1,4 @@ +import warnings from typing import Any, Optional, Type @@ -25,9 +26,10 @@ class InternalInstructor: if self.agent and not self.llm: self.llm = self.agent.function_calling_llm or self.agent.llm - # Lazy import - import instructor - from litellm import completion + with warnings.catch_warnings(): + warnings.simplefilter("ignore", UserWarning) + import instructor + from litellm import completion self._client = instructor.from_litellm( completion, diff --git a/src/crewai/utilities/token_counter_callback.py b/src/crewai/utilities/token_counter_callback.py index 06ad15022..46c7c68f9 100644 --- a/src/crewai/utilities/token_counter_callback.py +++ b/src/crewai/utilities/token_counter_callback.py @@ -1,3 +1,5 @@ +import warnings + from litellm.integrations.custom_logger import CustomLogger from litellm.types.utils import Usage @@ -12,11 +14,13 @@ class TokenCalcHandler(CustomLogger): if self.token_cost_process is None: return - usage: Usage = response_obj["usage"] - self.token_cost_process.sum_successful_requests(1) - self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens) - self.token_cost_process.sum_completion_tokens(usage.completion_tokens) - if usage.prompt_tokens_details: - self.token_cost_process.sum_cached_prompt_tokens( - usage.prompt_tokens_details.cached_tokens - ) + with warnings.catch_warnings(): + warnings.simplefilter("ignore", UserWarning) + usage: Usage = response_obj["usage"] + self.token_cost_process.sum_successful_requests(1) + self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens) + self.token_cost_process.sum_completion_tokens(usage.completion_tokens) + if usage.prompt_tokens_details: + self.token_cost_process.sum_cached_prompt_tokens( + usage.prompt_tokens_details.cached_tokens + ) diff --git a/tests/agent_test.py b/tests/agent_test.py index 6879a4519..c490a5e13 100644 --- a/tests/agent_test.py +++ b/tests/agent_test.py @@ -1445,44 +1445,43 @@ def test_llm_call_with_all_attributes(): @pytest.mark.vcr(filter_headers=["authorization"]) -def test_agent_with_ollama_gemma(): +def test_agent_with_ollama_llama3(): agent = Agent( role="test role", goal="test goal", backstory="test backstory", - llm=LLM( - model="ollama/gemma2:latest", - base_url="http://localhost:8080", - ), + llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"), ) assert isinstance(agent.llm, LLM) - assert agent.llm.model == "ollama/gemma2:latest" - assert agent.llm.base_url == "http://localhost:8080" + assert agent.llm.model == "ollama/llama3.2:3b" + assert agent.llm.base_url == "http://localhost:11434" - task = "Respond in 20 words. Who are you?" + task = "Respond in 20 words. Which model are you?" response = agent.llm.call([{"role": "user", "content": task}]) assert response assert len(response.split()) <= 25 # Allow a little flexibility in word count - assert "Gemma" in response or "AI" in response or "language model" in response + assert "Llama3" in response or "AI" in response or "language model" in response @pytest.mark.vcr(filter_headers=["authorization"]) -def test_llm_call_with_ollama_gemma(): +def test_llm_call_with_ollama_llama3(): llm = LLM( - model="ollama/gemma2:latest", - base_url="http://localhost:8080", + model="ollama/llama3.2:3b", + base_url="http://localhost:11434", temperature=0.7, max_tokens=30, ) - messages = [{"role": "user", "content": "Respond in 20 words. Who are you?"}] + messages = [ + {"role": "user", "content": "Respond in 20 words. Which model are you?"} + ] response = llm.call(messages) assert response assert len(response.split()) <= 25 # Allow a little flexibility in word count - assert "Gemma" in response or "AI" in response or "language model" in response + assert "Llama3" in response or "AI" in response or "language model" in response @pytest.mark.vcr(filter_headers=["authorization"]) @@ -1578,7 +1577,7 @@ def test_agent_execute_task_with_ollama(): role="test role", goal="test goal", backstory="test backstory", - llm=LLM(model="ollama/gemma2:latest", base_url="http://localhost:8080"), + llm=LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434"), ) task = Task( diff --git a/tests/cassettes/test_agent_execute_task_with_ollama.yaml b/tests/cassettes/test_agent_execute_task_with_ollama.yaml index 62f1fe37f..d8ecb4dde 100644 --- a/tests/cassettes/test_agent_execute_task_with_ollama.yaml +++ b/tests/cassettes/test_agent_execute_task_with_ollama.yaml @@ -1,42 +1,6 @@ interactions: - request: - body: !!binary | - CrcCCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSjgIKEgoQY3Jld2FpLnRl - bGVtZXRyeRJoChA/Q8UW5bidCRtKvri5fOaNEgh5qLzvLvZJkioQVG9vbCBVc2FnZSBFcnJvcjAB - OYjFVQr1TPgXQXCXhwr1TPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMHoCGAGFAQABAAAS - jQEKEChQTWQ07t26ELkZmP5RresSCHEivRGBpsP7KgpUb29sIFVzYWdlMAE5sKkbC/VM+BdB8MIc - C/VM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShkKCXRvb2xfbmFtZRIMCgpkdW1teV90 - b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA= - headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate - Connection: - - keep-alive - Content-Length: - - '314' - Content-Type: - - application/x-protobuf - User-Agent: - - OTel-OTLP-Exporter-Python/1.27.0 - method: POST - uri: https://telemetry.crewai.com:4319/v1/traces - response: - body: - string: "\n\0" - headers: - Content-Length: - - '2' - Content-Type: - - application/x-protobuf - Date: - - Tue, 24 Sep 2024 21:57:54 GMT - status: - code: 200 - message: OK -- request: - body: '{"model": "gemma2:latest", "prompt": "### System:\nYou are test role. test + body: '{"model": "llama3.2:3b", "prompt": "### System:\nYou are test role. test backstory\nYour personal goal is: test goal\nTo give my best complete final answer to the task use the exact following format:\n\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most @@ -46,7 +10,7 @@ interactions: explanation of AI\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:\n\n", - "options": {}, "stream": false}' + "options": {"stop": ["\nObservation:"]}, "stream": false}' headers: Accept: - '*/*' @@ -55,26 +19,26 @@ interactions: Connection: - keep-alive Content-Length: - - '815' + - '839' Content-Type: - application/json User-Agent: - - python-requests/2.31.0 + - python-requests/2.32.3 method: POST - uri: http://localhost:8080/api/generate + uri: http://localhost:11434/api/generate response: body: - string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:55.835715Z","response":"Thought: - I can explain AI in one sentence. \n\nFinal Answer: Artificial intelligence - (AI) is the ability of computer systems to perform tasks that typically require - human intelligence, such as learning, problem-solving, and decision-making. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,1479,235292,108,2045,708,2121,4731,235265,2121,135147,108,6922,3749,6789,603,235292,2121,6789,108,1469,2734,970,1963,3407,2048,3448,577,573,6911,1281,573,5463,2412,5920,235292,109,65366,235292,590,1490,798,2734,476,1775,3448,108,11263,10358,235292,3883,2048,3448,2004,614,573,1775,578,573,1546,3407,685,3077,235269,665,2004,614,17526,6547,235265,109,235285,44472,1281,1450,32808,235269,970,3356,12014,611,665,235341,109,6176,4926,235292,109,6846,12297,235292,36576,1212,16481,603,575,974,13060,109,1596,603,573,5246,12830,604,861,2048,3448,235292,586,974,235290,47366,15844,576,16481,108,4747,44472,2203,573,5579,3407,3381,685,573,2048,3448,235269,780,476,13367,235265,109,12694,235341,1417,603,50471,2845,577,692,235269,1281,573,8112,2506,578,2734,861,1963,14124,10358,235269,861,3356,12014,611,665,235341,109,65366,235292,109,107,108,106,2516,108,65366,235292,590,798,10200,16481,575,974,13060,235265,235248,109,11263,10358,235292,42456,17273,591,11716,235275,603,573,7374,576,6875,5188,577,3114,13333,674,15976,2817,3515,17273,235269,1582,685,6044,235269,3210,235290,60495,235269,578,4530,235290,14577,235265,139,108],"total_duration":3370959792,"load_duration":20611750,"prompt_eval_count":173,"prompt_eval_duration":688036000,"eval_count":51,"eval_duration":2660291000}' + string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:05:52.24992Z","response":"Final + Answer: Artificial Intelligence (AI) refers to the development of computer + systems capable of performing tasks that typically require human intelligence, + such as learning, problem-solving, decision-making, and perception.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,2675,527,1296,3560,13,1296,93371,198,7927,4443,5915,374,25,1296,5915,198,1271,3041,856,1888,4686,1620,4320,311,279,3465,1005,279,4839,2768,3645,1473,85269,25,358,1457,649,3041,264,2294,4320,198,19918,22559,25,4718,1620,4320,2011,387,279,2294,323,279,1455,4686,439,3284,11,433,2011,387,15632,7633,382,40,28832,1005,1521,20447,11,856,2683,14117,389,433,2268,14711,2724,1473,5520,5546,25,83017,1148,15592,374,304,832,11914,271,2028,374,279,1755,13186,369,701,1620,4320,25,362,832,1355,18886,16540,315,15592,198,9514,28832,471,279,5150,4686,2262,439,279,1620,4320,11,539,264,12399,382,11382,0,1115,374,48174,3062,311,499,11,1005,279,7526,2561,323,3041,701,1888,13321,22559,11,701,2683,14117,389,433,2268,85269,1473,128009,128006,78191,128007,271,19918,22559,25,59294,22107,320,15836,8,19813,311,279,4500,315,6500,6067,13171,315,16785,9256,430,11383,1397,3823,11478,11,1778,439,6975,11,3575,99246,11,5597,28846,11,323,21063,13],"total_duration":1461909875,"load_duration":39886208,"prompt_eval_count":181,"prompt_eval_duration":701000000,"eval_count":39,"eval_duration":719000000}' headers: Content-Length: - - '1662' + - '1537' Content-Type: - application/json; charset=utf-8 Date: - - Tue, 24 Sep 2024 21:57:55 GMT + - Thu, 02 Jan 2025 20:05:52 GMT status: code: 200 message: OK diff --git a/tests/cassettes/test_agent_with_ollama_gemma.yaml b/tests/cassettes/test_agent_with_ollama_gemma.yaml deleted file mode 100644 index 86e829fbc..000000000 --- a/tests/cassettes/test_agent_with_ollama_gemma.yaml +++ /dev/null @@ -1,397 +0,0 @@ -interactions: -- request: - body: !!binary | - CumTAQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5Er+TAQoSChBjcmV3YWku - dGVsZW1ldHJ5EqoHChDvqD2QZooz9BkEwtbWjp4OEgjxh72KACHvZSoMQ3JldyBDcmVhdGVkMAE5 - qMhNnvBM+BdBcO9PnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92 - ZXJzaW9uEggKBjMuMTEuN0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQy - YjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgy - MkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jl - d19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKxwIKC2Ny - ZXdfYWdlbnRzErcCCrQCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi - IiwgImlkIjogIjg1MGJjNWUwLTk4NTctNDhkOC1iNWZlLTJmZjk2OWExYTU3YiIsICJyb2xlIjog - InRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDQsICJtYXhfcnBtIjog - MTAsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0 - aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1h - eF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1KkAIKCmNyZXdfdGFza3MSgQIK - /gFbeyJrZXkiOiAiNGEzMWI4NTEzM2EzYTI5NGM2ODUzZGE3NTdkNGJhZTciLCAiaWQiOiAiOTc1 - ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBm - YWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUiLCAi - YWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgInRvb2xzX25h - bWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGFAQABAAASjgIKEP9UYSAOFQbZquSppN1j - IeUSCAgZmXUoJKFmKgxUYXNrIENyZWF0ZWQwATloPV+e8Ez4F0GYsl+e8Ez4F0ouCghjcmV3X2tl - eRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3X2lkEiYKJGY4YTA1 - OTA1LTk0OGEtNDQ0YS04NmJmLTJiNTNiNDkyYjgyMkouCgh0YXNrX2tleRIiCiA0YTMxYjg1MTMz - YTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDk3NWQ4MDIyLTFiZDEtNDYwZS04 - NjZhLWIyZmRjYmIwOGQ5YnoCGAGFAQABAAASkwEKEEfiywgqgiUXE3KoUbrnHDQSCGmv+iM7Wc1Z - KgpUb29sIFVzYWdlMAE5kOybnvBM+BdBIM+cnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42 - MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGF - AQABAAASkwEKEH7AHXpfmvwIkA45HB8YyY0SCAFRC+uJpsEZKgpUb29sIFVzYWdlMAE56PLdnvBM - +BdBYFbfnvBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBn - ZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkwEKEIDKKEbYU4lcJF+a - WsAVZwESCI+/La7oL86MKgpUb29sIFVzYWdlMAE5yIkgn/BM+BdBWGwhn/BM+BdKGgoOY3Jld2Fp - X3ZlcnNpb24SCAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0 - dGVtcHRzEgIYAXoCGAGFAQABAAASnAEKEMTZ2IhpLz6J2hJhHBQ8/M4SCEuWz+vjzYifKhNUb29s - IFJlcGVhdGVkIFVzYWdlMAE5mAVhn/BM+BdBKOhhn/BM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoG - MC42MS4wSh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoC - GAGFAQABAAASkAIKED8C+t95p855kLcXs5Nnt/sSCM4XAhL6u8O8Kg5UYXNrIEV4ZWN1dGlvbjAB - OdD8X57wTPgXQUgno5/wTPgXSi4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYw - NDJiMmYwM2YxSjEKB2NyZXdfaWQSJgokZjhhMDU5MDUtOTQ4YS00NDRhLTg2YmYtMmI1M2I0OTJi - ODIySi4KCHRhc2tfa2V5EiIKIDRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3SjEKB3Rh - c2tfaWQSJgokOTc1ZDgwMjItMWJkMS00NjBlLTg2NmEtYjJmZGNiYjA4ZDliegIYAYUBAAEAABLO - CwoQFlnZCfbZ3Dj0L9TAE5LrLBIIoFr7BZErFNgqDENyZXcgQ3JlYXRlZDABOVhDDaDwTPgXQSg/ - D6DwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYz - LjExLjdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2ZjNTcyZDBmNTlKMQoH - Y3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBlMGZKHAoMY3Jld19w - cm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29m - X3Rhc2tzEgIYAkobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSv4ECgtjcmV3X2FnZW50cxLu - BArrBFt7ImtleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICI0 - MjAzZjIyYi0wNWM3LTRiNjUtODBjMS1kM2Y0YmFlNzZhNDYiLCAicm9sZSI6ICJ0ZXN0IHJvbGUi - LCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAyLCAibWF4X3JwbSI6IDEwLCAiZnVuY3Rp - b25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVk - PyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGlt - aXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh - YmVlY2YxNDI1ZGI3IiwgImlkIjogImZjOTZjOTQ1LTY4ZDUtNDIxMy05NmNkLTNmYTAwNmUyZTYz - MCIsICJyb2xlIjogInRlc3Qgcm9sZTIiLCAidmVyYm9zZT8iOiB0cnVlLCAibWF4X2l0ZXIiOiAx - LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw - dC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlv - bj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/QMK - CmNyZXdfdGFza3MS7gMK6wNbeyJrZXkiOiAiMzIyZGRhZTNiYzgwYzFkNDViODVmYTc3NTZkYjg2 - NjUiLCAiaWQiOiAiOTVjYTg4NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkIiwgImFzeW5j - X2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6 - ICJ0ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1 - ODJiIiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI1ZTljYTdkNjRiNDIwNWJiN2M0N2Uw - YjNmY2I1ZDIxZiIsICJpZCI6ICI5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDAi - LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu - dF9yb2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVh - YmVlY2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogWyJnZXRfZmluYWxfYW5zd2VyIl19XXoCGAGF - AQABAAASjgIKEC/YM2OukRrSg+ZAev4VhGESCOQ5RvzSS5IEKgxUYXNrIENyZWF0ZWQwATmQJx6g - 8Ez4F0EgjR6g8Ez4F0ouCghjcmV3X2tleRIiCiA5NGMzMGQ2YzNiMmFjOGZiOTRiMmRjZmM1NzJk - MGY1OUoxCgdjcmV3X2lkEiYKJDIzMzYzNGM2LWU2ZDYtNDllNi04OGFlLWVhZTFhMzliMGUwZkou - Cgh0YXNrX2tleRIiCiAzMjJkZGFlM2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lk - EiYKJDk1Y2E4ODQyLTZhMTItNDBkOS1iMGQyLTRiNDM2MWJiZTU2ZHoCGAGFAQABAAASkAIKEHqZ - L8s3clXQyVTemNcTCcQSCA0tzK95agRQKg5UYXNrIEV4ZWN1dGlvbjABOQC8HqDwTPgXQdgNSqDw - TPgXSi4KCGNyZXdfa2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2Ny - ZXdfaWQSJgokMjMzNjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5 - EiIKIDMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokOTVjYTg4 - NDItNmExMi00MGQ5LWIwZDItNGI0MzYxYmJlNTZkegIYAYUBAAEAABKOAgoQjhKzodMUmQ8NWtdy - Uj99whIIBsGtAymZibwqDFRhc2sgQ3JlYXRlZDABOXjVVaDwTPgXQXhSVqDwTPgXSi4KCGNyZXdf - a2V5EiIKIDk0YzMwZDZjM2IyYWM4ZmI5NGIyZGNmYzU3MmQwZjU5SjEKB2NyZXdfaWQSJgokMjMz - NjM0YzYtZTZkNi00OWU2LTg4YWUtZWFlMWEzOWIwZTBmSi4KCHRhc2tfa2V5EiIKIDVlOWNhN2Q2 - NGI0MjA1YmI3YzQ3ZTBiM2ZjYjVkMjFmSjEKB3Rhc2tfaWQSJgokOTcyOTE4NmMtZDdiZS00ZGI0 - LWE5NGUtNjllOTk5NjUyNzAwegIYAYUBAAEAABKTAQoQx5IUsjAFMGNUaz5MHy20OBIIzl2tr25P - LL8qClRvb2wgVXNhZ2UwATkgt5Sg8Ez4F0GwFpag8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYw - LjYxLjBKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIY - AYUBAAEAABKQAgoQEkfcfCrzTYIM6GQXhknlexIIa/oxeT78OL8qDlRhc2sgRXhlY3V0aW9uMAE5 - WIFWoPBM+BdBuL/GoPBM+BdKLgoIY3Jld19rZXkSIgogOTRjMzBkNmMzYjJhYzhmYjk0YjJkY2Zj - NTcyZDBmNTlKMQoHY3Jld19pZBImCiQyMzM2MzRjNi1lNmQ2LTQ5ZTYtODhhZS1lYWUxYTM5YjBl - MGZKLgoIdGFza19rZXkSIgogNWU5Y2E3ZDY0YjQyMDViYjdjNDdlMGIzZmNiNWQyMWZKMQoHdGFz - a19pZBImCiQ5NzI5MTg2Yy1kN2JlLTRkYjQtYTk0ZS02OWU5OTk2NTI3MDB6AhgBhQEAAQAAEqwH - ChDrKBdEe+Z5276g9fgg6VzjEgiJfnDwsv1SrCoMQ3JldyBDcmVhdGVkMAE5MLQYofBM+BdBQFIa - ofBM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMu - MTEuN0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1MTQ3NjcwMDAzNDExMEoxCgdj - cmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1NGZlNWZkN0ocCgxjcmV3X3By - b2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2Zf - dGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFKyQIKC2NyZXdfYWdlbnRzErkC - CrYCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJiIiwgImlkIjogIjk4 - YmIwNGYxLTBhZGMtNGZiNC04YzM2LWM3M2Q1MzQ1ZGRhZCIsICJyb2xlIjogInRlc3Qgcm9sZSIs - ICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDEsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0 - aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvIiwgImRlbGVnYXRpb25fZW5hYmxl - ZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xp - bWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUqQAgoKY3Jld190YXNrcxKBAgr+AVt7ImtleSI6 - ICJmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhYyIsICJpZCI6ICIxZjRhYzJhYS03YmQ4 - LTQ1NWQtODgyMC1jMzZmMjJjMDY4MzciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVt - YW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9rZXki - OiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBbImdl - dF9maW5hbF9hbnN3ZXIiXX1degIYAYUBAAEAABKOAgoQ0/vrakH7zD0uSvmVBUV8lxIIYe4YKcYG - hNgqDFRhc2sgQ3JlYXRlZDABOdBXKqHwTPgXQcCtKqHwTPgXSi4KCGNyZXdfa2V5EiIKIDczYWFj - Mjg1ZTY3NDY2NjdmNzUxNDc2NzAwMDM0MTEwSjEKB2NyZXdfaWQSJgokODQ0NjRiOGUtNGJmNy00 - NGJjLTkyZTEtYThkMTU0ZmU1ZmQ3Si4KCHRhc2tfa2V5EiIKIGY3YTlmN2JiMWFlZTRiNmVmMmM1 - MjZkMGE4YzJmMmFjSjEKB3Rhc2tfaWQSJgokMWY0YWMyYWEtN2JkOC00NTVkLTg4MjAtYzM2ZjIy - YzA2ODM3egIYAYUBAAEAABKkAQoQ5GDzHNlSdlcVDdxsI3abfRIIhYu8fZS3iA4qClRvb2wgVXNh - Z2UwATnIi2eh8Ez4F0FYbmih8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHwoJdG9v - bF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBSg8KA2xsbRIICgZncHQt - NG96AhgBhQEAAQAAEpACChAy85Jfr/EEIe1THU8koXoYEgjlkNn7xfysjioOVGFzayBFeGVjdXRp - b24wATm42Cqh8Ez4F0GgxZah8Ez4F0ouCghjcmV3X2tleRIiCiA3M2FhYzI4NWU2NzQ2NjY3Zjc1 - MTQ3NjcwMDAzNDExMEoxCgdjcmV3X2lkEiYKJDg0NDY0YjhlLTRiZjctNDRiYy05MmUxLWE4ZDE1 - NGZlNWZkN0ouCgh0YXNrX2tleRIiCiBmN2E5ZjdiYjFhZWU0YjZlZjJjNTI2ZDBhOGMyZjJhY0ox - Cgd0YXNrX2lkEiYKJDFmNGFjMmFhLTdiZDgtNDU1ZC04ODIwLWMzNmYyMmMwNjgzN3oCGAGFAQAB - AAASrAcKEG0ZVq5Ww+/A0wOY3HmKgq4SCMe0ooxqjqBlKgxDcmV3IENyZWF0ZWQwATlwmISi8Ez4 - F0HYUYai8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24S - CAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIGQ1NTExM2JlNGFhNDFiYTY0M2QzMjYwNDJiMmYwM2Yx - SjEKB2NyZXdfaWQSJgokNzkyMWVlYmItMWI4NS00MzNjLWIxMDAtZDU4MmMyOTg5MzBkShwKDGNy - ZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJl - cl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrJAgoLY3Jld19hZ2Vu - dHMSuQIKtgJbeyJrZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQi - OiAiZmRiZDI1MWYtYzUwOC00YmFhLTkwNjctN2U5YzQ2ZGZiZTJhIiwgInJvbGUiOiAidGVzdCBy - b2xlIiwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogNiwgIm1heF9ycG0iOiBudWxsLCAi - ZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9l - bmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0 - cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpACCgpjcmV3X3Rhc2tzEoECCv4BW3si - a2V5IjogIjRhMzFiODUxMzNhM2EyOTRjNjg1M2RhNzU3ZDRiYWU3IiwgImlkIjogIjA2YWFmM2Y1 - LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OSIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2Us - ICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50 - X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6 - IFsiZ2V0X2ZpbmFsX2Fuc3dlciJdfV16AhgBhQEAAQAAEo4CChDT+zPZHwfacDilkzaZJ9uGEgip - Kr5r62JB+ioMVGFzayBDcmVhdGVkMAE56KeTovBM+BdB8PmTovBM+BdKLgoIY3Jld19rZXkSIgog - ZDU1MTEzYmU0YWE0MWJhNjQzZDMyNjA0MmIyZjAzZjFKMQoHY3Jld19pZBImCiQ3OTIxZWViYi0x - Yjg1LTQzM2MtYjEwMC1kNTgyYzI5ODkzMGRKLgoIdGFza19rZXkSIgogNGEzMWI4NTEzM2EzYTI5 - NGM2ODUzZGE3NTdkNGJhZTdKMQoHdGFza19pZBImCiQwNmFhZjNmNS0xOTg3LTQwMWEtOWM5NC1m - N2YzNWJkMzA4Nzl6AhgBhQEAAQAAEpMBChCl85ZcL2Fa0N5QTl6EsIfnEghyDo3bxT+AkyoKVG9v - bCBVc2FnZTABOVBA2aLwTPgXQYAy2qLwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEof - Cgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA - EpwBChB22uwKhaur9zmeoeEMaRKzEgjrtSEzMbRdIioTVG9vbCBSZXBlYXRlZCBVc2FnZTABOQga - C6PwTPgXQaDRC6PwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUS - EgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpMBChArAfcRpE+W - 02oszyzccbaWEghTAO9J3zq/kyoKVG9vbCBVc2FnZTABORBRTqPwTPgXQegnT6PwTPgXShoKDmNy - ZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoO - CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpwBChBdtM3p3aqT7wTGaXi6el/4Egie6lFQpa+AfioT - VG9vbCBSZXBlYXRlZCBVc2FnZTABOdBg2KPwTPgXQehW2aPwTPgXShoKDmNyZXdhaV92ZXJzaW9u - EggKBjAuNjEuMEofCgl0b29sX25hbWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxIC - GAF6AhgBhQEAAQAAEpMBChDq4OuaUKkNoi6jlMyahPJpEgg1MFDHktBxNSoKVG9vbCBVc2FnZTAB - ORD/K6TwTPgXQZgMLaTwTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuNjEuMEofCgl0b29sX25h - bWUSEgoQZ2V0X2ZpbmFsX2Fuc3dlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpACChBhvTmu - QWP+bx9JMmGpt+w5Egh1J17yki7s8ioOVGFzayBFeGVjdXRpb24wATnoJJSi8Ez4F0HwNX6k8Ez4 - F0ouCghjcmV3X2tleRIiCiBkNTUxMTNiZTRhYTQxYmE2NDNkMzI2MDQyYjJmMDNmMUoxCgdjcmV3 - X2lkEiYKJDc5MjFlZWJiLTFiODUtNDMzYy1iMTAwLWQ1ODJjMjk4OTMwZEouCgh0YXNrX2tleRIi - CiA0YTMxYjg1MTMzYTNhMjk0YzY4NTNkYTc1N2Q0YmFlN0oxCgd0YXNrX2lkEiYKJDA2YWFmM2Y1 - LTE5ODctNDAxYS05Yzk0LWY3ZjM1YmQzMDg3OXoCGAGFAQABAAASrg0KEOJZEqiJ7LTTX/J+tuLR - stQSCHKjy4tIcmKEKgxDcmV3IENyZWF0ZWQwATmIEuGk8Ez4F0FYDuOk8Ez4F0oaCg5jcmV3YWlf - dmVyc2lvbhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5 - EiIKIDExMWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5 - MmQtYjg3NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50 - aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGANKGwoVY3Jl - d19udW1iZXJfb2ZfYWdlbnRzEgIYAkqEBQoLY3Jld19hZ2VudHMS9AQK8QRbeyJrZXkiOiAiZTE0 - OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiZmYzOTE0OGEtZWI2NS00Nzkx - LWI3MTMtM2Q4ZmE1YWQ5NTJlIiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFs - c2UsICJtYXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xs - bSI6ICIiLCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJh - bGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29s - c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiZTdlOGVlYTg4NmJjYjhmMTA0NWFiZWVjZjE0MjVkYjci - LCAiaWQiOiAiYzYyNDJmNDMtNmQ2Mi00N2U4LTliYmMtNjM0ZDQwYWI4YTQ2IiwgInJvbGUiOiAi - dGVzdCByb2xlMiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0i - OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVs - ZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2Us - ICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dStcFCgpjcmV3X3Rhc2tz - EsgFCsUFW3sia2V5IjogIjMyMmRkYWUzYmM4MGMxZDQ1Yjg1ZmE3NzU2ZGI4NjY1IiwgImlkIjog - IjRmZDZhZDdiLTFjNWMtNDE1ZC1hMWQ4LTgwYzExZGNjMTY4NiIsICJhc3luY19leGVjdXRpb24/ - IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xl - IiwgImFnZW50X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29s - c19uYW1lcyI6IFtdfSwgeyJrZXkiOiAiY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTki - LCAiaWQiOiAiOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjIiwgImFzeW5jX2V4 - ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0 - ZXN0IHJvbGUiLCAiYWdlbnRfa2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZlNzI1ODJi - IiwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICJlMGIxM2UxMGQ3YTE0NmRjYzRjNDg4ZmNm - OGQ3NDhhMCIsICJpZCI6ICI4NjExZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWYiLCAi - YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y - b2xlIjogInRlc3Qgcm9sZTIiLCAiYWdlbnRfa2V5IjogImU3ZThlZWE4ODZiY2I4ZjEwNDVhYmVl - Y2YxNDI1ZGI3IiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEMbX6YsWK7RRf4L1 - NBRKD6cSCFLJiNmspsyjKgxUYXNrIENyZWF0ZWQwATnonPGk8Ez4F0EotvKk8Ez4F0ouCghjcmV3 - X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYKJGFh - YmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiAzMjJkZGFl - M2JjODBjMWQ0NWI4NWZhNzc1NmRiODY2NUoxCgd0YXNrX2lkEiYKJDRmZDZhZDdiLTFjNWMtNDE1 - ZC1hMWQ4LTgwYzExZGNjMTY4NnoCGAGFAQABAAASkAIKEM9JnUNanFbE9AtnSxqA7H8SCBWlG0WJ - sMgKKg5UYXNrIEV4ZWN1dGlvbjABOfDo8qTwTPgXQWhEH6XwTPgXSi4KCGNyZXdfa2V5EiIKIDEx - MWI4NzJkOGYwY2Y3MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3 - NC00NTZmLWE0NzAtM2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIDMyMmRkYWUzYmM4MGMxZDQ1 - Yjg1ZmE3NzU2ZGI4NjY1SjEKB3Rhc2tfaWQSJgokNGZkNmFkN2ItMWM1Yy00MTVkLWExZDgtODBj - MTFkY2MxNjg2egIYAYUBAAEAABKOAgoQaQALCJNe5ByN4Wu7FE0kABIIYW/UfVfnYscqDFRhc2sg - Q3JlYXRlZDABOWhzLKXwTPgXQSD8LKXwTPgXSi4KCGNyZXdfa2V5EiIKIDExMWI4NzJkOGYwY2Y3 - MDNmMmVmZWYwNGNmM2FjNzk4SjEKB2NyZXdfaWQSJgokYWFiYmU5MmQtYjg3NC00NTZmLWE0NzAt - M2FmMDc4ZTdjYThlSi4KCHRhc2tfa2V5EiIKIGNjNDg3NmY2ZTU4OGU3MTM0OWJiZDNhNjU4ODhj - M2U5SjEKB3Rhc2tfaWQSJgokOTFlYWFhMWMtMWI4ZC00MDcxLTk2ZmQtM2QxZWVkMjhjMzZjegIY - AYUBAAEAABKQAgoQpPfkgFlpIsR/eN2zn+x3MRIILoWF4/HvceAqDlRhc2sgRXhlY3V0aW9uMAE5 - GCctpfBM+BdBQLNapfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0 - Y2YzYWM3OThKMQoHY3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2Nh - OGVKLgoIdGFza19rZXkSIgogY2M0ODc2ZjZlNTg4ZTcxMzQ5YmJkM2E2NTg4OGMzZTlKMQoHdGFz - a19pZBImCiQ5MWVhYWExYy0xYjhkLTQwNzEtOTZmZC0zZDFlZWQyOGMzNmN6AhgBhQEAAQAAEo4C - ChCdvXmXZRltDxEwZx2XkhWhEghoKdomHHhLGSoMVGFzayBDcmVhdGVkMAE54HpmpfBM+BdB4Pdm - pfBM+BdKLgoIY3Jld19rZXkSIgogMTExYjg3MmQ4ZjBjZjcwM2YyZWZlZjA0Y2YzYWM3OThKMQoH - Y3Jld19pZBImCiRhYWJiZTkyZC1iODc0LTQ1NmYtYTQ3MC0zYWYwNzhlN2NhOGVKLgoIdGFza19r - ZXkSIgogZTBiMTNlMTBkN2ExNDZkY2M0YzQ4OGZjZjhkNzQ4YTBKMQoHdGFza19pZBImCiQ4NjEx - ZjhjZS1jNDVlLTQ2OTgtYWEyMS1jMGJkNzdhOGY2ZWZ6AhgBhQEAAQAAEpACChAIvs/XQL53haTt - NV8fk6geEgicgSOcpcYulyoOVGFzayBFeGVjdXRpb24wATnYImel8Ez4F0Gw5ZSl8Ez4F0ouCghj - cmV3X2tleRIiCiAxMTFiODcyZDhmMGNmNzAzZjJlZmVmMDRjZjNhYzc5OEoxCgdjcmV3X2lkEiYK - JGFhYmJlOTJkLWI4NzQtNDU2Zi1hNDcwLTNhZjA3OGU3Y2E4ZUouCgh0YXNrX2tleRIiCiBlMGIx - M2UxMGQ3YTE0NmRjYzRjNDg4ZmNmOGQ3NDhhMEoxCgd0YXNrX2lkEiYKJDg2MTFmOGNlLWM0NWUt - NDY5OC1hYTIxLWMwYmQ3N2E4ZjZlZnoCGAGFAQABAAASvAcKEARTPn0s+U/k8GclUc+5rRoSCHF3 - KCh8OS0FKgxDcmV3IENyZWF0ZWQwATlo+Pul8Ez4F0EQ0f2l8Ez4F0oaCg5jcmV3YWlfdmVyc2lv - bhIICgYwLjYxLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43Si4KCGNyZXdfa2V5EiIKIDQ5 - NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMz - Mi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEK - C2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1i - ZXJfb2ZfYWdlbnRzEgIYAUrbAgoLY3Jld19hZ2VudHMSywIKyAJbeyJrZXkiOiAiZTE0OGU1MzIw - MjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAiaWQiOiAiNGFkYzNmMmItN2IwNC00MDRlLWEwNDQt - N2JkNjVmYTMyZmE4IiwgInJvbGUiOiAidGVzdCByb2xlIiwgInZlcmJvc2U/IjogZmFsc2UsICJt - YXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIi - LCAibGxtIjogImdwdC00byIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19j - b2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1l - cyI6IFsibGVhcm5fYWJvdXRfYWkiXX1dSo4CCgpjcmV3X3Rhc2tzEv8BCvwBW3sia2V5IjogImYy - NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjIiwgImlkIjogIjg2YzZiODE2LTgyOWMtNDUx - Zi1iMDZkLTUyZjQ4YTdhZWJiMyIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9p - bnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgImFnZW50X2tleSI6ICJl - MTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJ0b29sc19uYW1lcyI6IFsibGVhcm5f - YWJvdXRfYWkiXX1degIYAYUBAAEAABKOAgoQZWSU3+i71QSqlD8iiLdyWBII1Pawtza2ZHsqDFRh - c2sgQ3JlYXRlZDABOdj2FKbwTPgXQZhUFabwTPgXSi4KCGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3 - YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokOWMwNzg3NWUtMTMzMi00MmMzLWFh - ZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRm - ZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIz - egIYAYUBAAEAABKRAQoQl3nNMLhrOg+OgsWWX6A9LxIINbCKrQzQ3JkqClRvb2wgVXNhZ2UwATlA - TlCm8Ez4F0FASFGm8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBKHQoJdG9vbF9uYW1l - EhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEL9YI/QwoVBJ - 1HBkTLyQxOESCCcKWhev/Dc8Kg5UYXNrIEV4ZWN1dGlvbjABOXiDFabwTPgXQcjEfqbwTPgXSi4K - CGNyZXdfa2V5EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQS - JgokOWMwNzg3NWUtMTMzMi00MmMzLWFhZTEtZjNjMjc1YTQyNjYwSi4KCHRhc2tfa2V5EiIKIGYy - NTk3Yzc4NjdmYmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokODZjNmI4MTYtODI5 - Yy00NTFmLWIwNmQtNTJmNDhhN2FlYmIzegIYAYUBAAEAABLBBwoQ0Le1256mT8wmcvnuLKYeNRII - IYBlVsTs+qEqDENyZXcgQ3JlYXRlZDABOYCBiKrwTPgXQRBeiqrwTPgXShoKDmNyZXdhaV92ZXJz - aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog - NDk0ZjM2NTcyMzdhZDhhMzAzNWIyZjFiZWVjZGM2NzdKMQoHY3Jld19pZBImCiQyN2VlMGYyYy1h - ZjgwLTQxYWMtYjg3ZC0xNmViYWQyMTVhNTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK - EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251 - bWJlcl9vZl9hZ2VudHMSAhgBSuACCgtjcmV3X2FnZW50cxLQAgrNAlt7ImtleSI6ICJlMTQ4ZTUz - MjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgyYiIsICJpZCI6ICJmMTYyMTFjNS00YWJlLTRhZDAtOWI0 - YS0yN2RmMTJhODkyN2UiLCAicm9sZSI6ICJ0ZXN0IHJvbGUiLCAidmVyYm9zZT8iOiBmYWxzZSwg - Im1heF9pdGVyIjogMiwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAi - Z3B0LTRvIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAi - YWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9v - bHNfbmFtZXMiOiBbImxlYXJuX2Fib3V0X2FpIl19XUqOAgoKY3Jld190YXNrcxL/AQr8AVt7Imtl - eSI6ICJmMjU5N2M3ODY3ZmJlMzI0ZGM2NWRjMDhkZmRiZmM2YyIsICJpZCI6ICJjN2FiOWRiYi0y - MTc4LTRmOGItOGFiNi1kYTU1YzE0YTBkMGMiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAi - aHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJhZ2VudF9r - ZXkiOiAiZTE0OGU1MzIwMjkzNDk5ZjhjZWJlYTgyNmU3MjU4MmIiLCAidG9vbHNfbmFtZXMiOiBb - ImxlYXJuX2Fib3V0X2FpIl19XXoCGAGFAQABAAASjgIKECr4ueCUCo/tMB7EuBQt6TcSCD/UepYl - WGqAKgxUYXNrIENyZWF0ZWQwATk4kpyq8Ez4F0Hg85yq8Ez4F0ouCghjcmV3X2tleRIiCiA0OTRm - MzY1NzIzN2FkOGEzMDM1YjJmMWJlZWNkYzY3N0oxCgdjcmV3X2lkEiYKJDI3ZWUwZjJjLWFmODAt - NDFhYy1iODdkLTE2ZWJhZDIxNWE1MkouCgh0YXNrX2tleRIiCiBmMjU5N2M3ODY3ZmJlMzI0ZGM2 - NWRjMDhkZmRiZmM2Y0oxCgd0YXNrX2lkEiYKJGM3YWI5ZGJiLTIxNzgtNGY4Yi04YWI2LWRhNTVj - MTRhMGQwY3oCGAGFAQABAAASeQoQkj0vmbCBIZPi33W9KrvrYhIIM2g73dOAN9QqEFRvb2wgVXNh - Z2UgRXJyb3IwATnQgsyr8Ez4F0GghM2r8Ez4F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjYxLjBK - DwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASeQoQavr4/1SWr8x7HD5mAzlM0hIIXPx740Skkd0q - EFRvb2wgVXNhZ2UgRXJyb3IwATkouH9C8Uz4F0FQ1YBC8Uz4F0oaCg5jcmV3YWlfdmVyc2lvbhII - CgYwLjYxLjBKDwoDbGxtEggKBmdwdC00b3oCGAGFAQABAAASkAIKEIgmJ3QURJvSsEifMScSiUsS - CCyiPHcZT8AnKg5UYXNrIEV4ZWN1dGlvbjABOcAinarwTPgXQeBEynvxTPgXSi4KCGNyZXdfa2V5 - EiIKIDQ5NGYzNjU3MjM3YWQ4YTMwMzViMmYxYmVlY2RjNjc3SjEKB2NyZXdfaWQSJgokMjdlZTBm - MmMtYWY4MC00MWFjLWI4N2QtMTZlYmFkMjE1YTUySi4KCHRhc2tfa2V5EiIKIGYyNTk3Yzc4Njdm - YmUzMjRkYzY1ZGMwOGRmZGJmYzZjSjEKB3Rhc2tfaWQSJgokYzdhYjlkYmItMjE3OC00ZjhiLThh - YjYtZGE1NWMxNGEwZDBjegIYAYUBAAEAABLEBwoQY+GZuYkP6mwdaVQQc11YuhII7ADKOlFZlzQq - DENyZXcgQ3JlYXRlZDABObCoi3zxTPgXQeCUjXzxTPgXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAu - NjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5 - ODU5YTY3ZWVjODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiQxMmE0OTFlNS00NDgwLTQ0MTYt - OTAxYi1iMmI1N2U1ZWU4ZThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19t - ZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9h - Z2VudHMSAhgBSt8CCgtjcmV3X2FnZW50cxLPAgrMAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZh - YzA1YjUzM2Q3NWU4ODkzYiIsICJpZCI6ICI5NjljZjhlMy0yZWEwLTQ5ZjgtODNlMS02MzEzYmE4 - ODc1ZjUiLCAicm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4 - X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg - ImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29k - ZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMi - OiBbImdldCBncmVldGluZ3MiXX1dSpICCgpjcmV3X3Rhc2tzEoMCCoACW3sia2V5IjogImEyNzdi - MzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3IiwgImlkIjogImIwMTg0NTI2LTJlOWItNDA0My1h - M2JiLTFiM2QzNWIxNTNhOCIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1 - dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRGF0YSBTY2llbnRpc3QiLCAiYWdlbnRfa2V5Ijog - IjIyYWNkNjExZTQ0ZWY1ZmFjMDViNTMzZDc1ZTg4OTNiIiwgInRvb2xzX25hbWVzIjogWyJnZXQg - Z3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEI/rrKkPz08VpVWNehfvxJ0SCIpeq76twGj3KgxU - YXNrIENyZWF0ZWQwATlA9aR88Uz4F0HoVqV88Uz4F0ouCghjcmV3X2tleRIiCiA3ZTY2MDg5ODk4 - NTlhNjdlZWM4OGVlZjdmY2U4NTIyNUoxCgdjcmV3X2lkEiYKJDEyYTQ5MWU1LTQ0ODAtNDQxNi05 - MDFiLWIyYjU3ZTVlZThlOEouCgh0YXNrX2tleRIiCiBhMjc3YjM0YjJjMTQ2ZjBjNTZjNWUxMzU2 - ZThmOGE1N0oxCgd0YXNrX2lkEiYKJGIwMTg0NTI2LTJlOWItNDA0My1hM2JiLTFiM2QzNWIxNTNh - OHoCGAGFAQABAAASkAEKEKKr5LR8SkqfqqktFhniLdkSCPMnqI2ma9UoKgpUb29sIFVzYWdlMAE5 - sCHgfPFM+BdB+A/hfPFM+BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC42MS4wShwKCXRvb2xfbmFt - ZRIPCg1HZXQgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkAIKEOj2bALdBlz6 - 1kP1MvHE5T0SCLw4D7D331IOKg5UYXNrIEV4ZWN1dGlvbjABOeCBpXzxTPgXQSjiEH3xTPgXSi4K - CGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQS - JgokMTJhNDkxZTUtNDQ4MC00NDE2LTkwMWItYjJiNTdlNWVlOGU4Si4KCHRhc2tfa2V5EiIKIGEy - NzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4YTU3SjEKB3Rhc2tfaWQSJgokYjAxODQ1MjYtMmU5 - Yi00MDQzLWEzYmItMWIzZDM1YjE1M2E4egIYAYUBAAEAABLQBwoQLjz7NWyGPgGU4tVFJ0sh9BII - N6EzU5f/sykqDENyZXcgQ3JlYXRlZDABOajOcX3xTPgXQUCAc33xTPgXShoKDmNyZXdhaV92ZXJz - aW9uEggKBjAuNjEuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKLgoIY3Jld19rZXkSIgog - YzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ1N2Y0NjVhNC03 - Zjk1LTQ5Y2MtODNmZC0zZTIwNWRhZDBjZTJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK - EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251 - bWJlcl9vZl9hZ2VudHMSAhgBSuUCCgtjcmV3X2FnZW50cxLVAgrSAlt7ImtleSI6ICI5OGYzYjFk - NDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICJjZjcyZDlkNy01MjQwLTRkMzEtYjA2 - Mi0xMmNjMDU2OGNjM2MiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJib3NlPyI6 - IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu - Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl - LCAiYWxsb3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAi - dG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1dSpgCCgpjcmV3X3Rhc2tzEokCCoYC - W3sia2V5IjogIjgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmIiwgImlkIjogIjUxNTJk - MmQ2LWYwODYtNGIyMi1hOGMxLTMyODA5NzU1NjZhZCIsICJhc3luY19leGVjdXRpb24/IjogZmFs - c2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiRnJpZW5kbHkgTmVpZ2hi - b3IiLCAiYWdlbnRfa2V5IjogIjk4ZjNiMWQ0N2NlOTY5Y2YwNTc3MjdiNzg0MTQyNWNkIiwgInRv - b2xzX25hbWVzIjogWyJkZWNpZGUgZ3JlZXRpbmdzIl19XXoCGAGFAQABAAASjgIKEM+95r2LzVVg - kqAMolHjl9oSCN9WyhdF/ucVKgxUYXNrIENyZWF0ZWQwATnoCoJ98Uz4F0HwXIJ98Uz4F0ouCghj - cmV3X2tleRIiCiBjMzA3NjAwOTMyNjc2MTQ0NGQ1N2M3MWQxZGEzZjI3Y0oxCgdjcmV3X2lkEiYK - JDU3ZjQ2NWE0LTdmOTUtNDljYy04M2ZkLTNlMjA1ZGFkMGNlMkouCgh0YXNrX2tleRIiCiA4MGQ3 - YmNkNDkwOTkyOTAwODM4MzJmMGU5ODMzODBkZkoxCgd0YXNrX2lkEiYKJDUxNTJkMmQ2LWYwODYt - NGIyMi1hOGMxLTMyODA5NzU1NjZhZHoCGAGFAQABAAASkwEKENJjTKn4eTP/P11ERMIGcdYSCIKF - bGEmcS7bKgpUb29sIFVzYWdlMAE5EFu5ffFM+BdBoD26ffFM+BdKGgoOY3Jld2FpX3ZlcnNpb24S - CAoGMC42MS4wSh8KCXRvb2xfbmFtZRISChBEZWNpZGUgR3JlZXRpbmdzSg4KCGF0dGVtcHRzEgIY - AXoCGAGFAQABAAASkAIKEG29htC06tLF7ihE5Yz6NyMSCAAsKzOcj25nKg5UYXNrIEV4ZWN1dGlv - bjABOQCEgn3xTPgXQfgg7X3xTPgXSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3 - YzcxZDFkYTNmMjdjSjEKB2NyZXdfaWQSJgokNTdmNDY1YTQtN2Y5NS00OWNjLTgzZmQtM2UyMDVk - YWQwY2UySi4KCHRhc2tfa2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEK - B3Rhc2tfaWQSJgokNTE1MmQyZDYtZjA4Ni00YjIyLWE4YzEtMzI4MDk3NTU2NmFkegIYAYUBAAEA - AA== - headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate - Connection: - - keep-alive - Content-Length: - - '18925' - Content-Type: - - application/x-protobuf - User-Agent: - - OTel-OTLP-Exporter-Python/1.27.0 - method: POST - uri: https://telemetry.crewai.com:4319/v1/traces - response: - body: - string: "\n\0" - headers: - Content-Length: - - '2' - Content-Type: - - application/x-protobuf - Date: - - Tue, 24 Sep 2024 21:57:39 GMT - status: - code: 200 - message: OK -- request: - body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who - are you?\n\n", "options": {}, "stream": false}' - headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate - Connection: - - keep-alive - Content-Length: - - '120' - Content-Type: - - application/json - User-Agent: - - python-requests/2.31.0 - method: POST - uri: http://localhost:8080/api/generate - response: - body: - string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:51.284303Z","response":"I - am Gemma, an open-weights AI assistant developed by Google DeepMind. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,6990,731,6238,20555,35777,235265,139,108],"total_duration":14046647083,"load_duration":12942541833,"prompt_eval_count":25,"prompt_eval_duration":177695000,"eval_count":19,"eval_duration":923120000}' - headers: - Content-Length: - - '579' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 24 Sep 2024 21:57:51 GMT - status: - code: 200 - message: OK -version: 1 diff --git a/tests/cassettes/test_agent_with_ollama_llama3.yaml b/tests/cassettes/test_agent_with_ollama_llama3.yaml new file mode 100644 index 000000000..beb146254 --- /dev/null +++ b/tests/cassettes/test_agent_with_ollama_llama3.yaml @@ -0,0 +1,36 @@ +interactions: +- request: + body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Who + which model are you?\n\n", "options": {"stop": ["\nObservation:"]}, "stream": + false}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '156' + Content-Type: + - application/json + User-Agent: + - python-requests/2.32.3 + method: POST + uri: http://localhost:11434/api/generate + response: + body: + string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:07:07.623404Z","response":"I''m + an AI designed to assist and communicate with users, utilizing a combination + of natural language processing models.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,10699,902,1646,527,499,1980,128009,128006,78191,128007,271,40,2846,459,15592,6319,311,7945,323,19570,449,3932,11,35988,264,10824,315,5933,4221,8863,4211,13],"total_duration":1076617833,"load_duration":46505416,"prompt_eval_count":40,"prompt_eval_duration":626000000,"eval_count":22,"eval_duration":399000000}' + headers: + Content-Length: + - '690' + Content-Type: + - application/json; charset=utf-8 + Date: + - Thu, 02 Jan 2025 20:07:07 GMT + status: + code: 200 + message: OK +version: 1 diff --git a/tests/cassettes/test_llm_call_with_ollama_gemma.yaml b/tests/cassettes/test_llm_call_with_ollama_gemma.yaml deleted file mode 100644 index 9735ae23e..000000000 --- a/tests/cassettes/test_llm_call_with_ollama_gemma.yaml +++ /dev/null @@ -1,35 +0,0 @@ -interactions: -- request: - body: '{"model": "gemma2:latest", "prompt": "### User:\nRespond in 20 words. Who - are you?\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream": - false}' - headers: - Accept: - - '*/*' - Accept-Encoding: - - gzip, deflate - Connection: - - keep-alive - Content-Length: - - '157' - Content-Type: - - application/json - User-Agent: - - python-requests/2.31.0 - method: POST - uri: http://localhost:8080/api/generate - response: - body: - string: '{"model":"gemma2:latest","created_at":"2024-09-24T21:57:52.329049Z","response":"I - am Gemma, an open-weights AI assistant trained by Google DeepMind. \n","done":true,"done_reason":"stop","context":[106,1645,108,6176,4926,235292,108,54657,575,235248,235284,235276,3907,235265,7702,708,692,235336,109,107,108,106,2516,108,235285,1144,137061,235269,671,2174,235290,30316,16481,20409,17363,731,6238,20555,35777,235265,139,108],"total_duration":991843667,"load_duration":31664750,"prompt_eval_count":25,"prompt_eval_duration":51409000,"eval_count":19,"eval_duration":908132000}' - headers: - Content-Length: - - '572' - Content-Type: - - application/json; charset=utf-8 - Date: - - Tue, 24 Sep 2024 21:57:52 GMT - status: - code: 200 - message: OK -version: 1 diff --git a/tests/cassettes/test_llm_call_with_ollama_llama3.yaml b/tests/cassettes/test_llm_call_with_ollama_llama3.yaml new file mode 100644 index 000000000..c1cee2cc8 --- /dev/null +++ b/tests/cassettes/test_llm_call_with_ollama_llama3.yaml @@ -0,0 +1,36 @@ +interactions: +- request: + body: '{"model": "llama3.2:3b", "prompt": "### User:\nRespond in 20 words. Which + model are you??\n\n", "options": {"num_predict": 30, "temperature": 0.7}, "stream": + false}' + headers: + Accept: + - '*/*' + Accept-Encoding: + - gzip, deflate + Connection: + - keep-alive + Content-Length: + - '164' + Content-Type: + - application/json + User-Agent: + - python-requests/2.32.3 + method: POST + uri: http://localhost:11434/api/generate + response: + body: + string: '{"model":"llama3.2:3b","created_at":"2025-01-02T20:24:24.812595Z","response":"I''m + an AI, specifically a large language model, designed to understand and respond + to user queries with accuracy.","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,66454,304,220,508,4339,13,16299,1646,527,499,71291,128009,128006,78191,128007,271,40,2846,459,15592,11,11951,264,3544,4221,1646,11,6319,311,3619,323,6013,311,1217,20126,449,13708,13],"total_duration":827817584,"load_duration":41560542,"prompt_eval_count":39,"prompt_eval_duration":384000000,"eval_count":23,"eval_duration":400000000}' + headers: + Content-Length: + - '683' + Content-Type: + - application/json; charset=utf-8 + Date: + - Thu, 02 Jan 2025 20:24:24 GMT + status: + code: 200 + message: OK +version: 1 diff --git a/tests/cli/tools/test_main.py b/tests/cli/tools/test_main.py index 10c29b920..b06c0b28c 100644 --- a/tests/cli/tools/test_main.py +++ b/tests/cli/tools/test_main.py @@ -28,9 +28,10 @@ def test_create_success(mock_subprocess): with in_temp_dir(): tool_command = ToolCommand() - with patch.object(tool_command, "login") as mock_login, patch( - "sys.stdout", new=StringIO() - ) as fake_out: + with ( + patch.object(tool_command, "login") as mock_login, + patch("sys.stdout", new=StringIO()) as fake_out, + ): tool_command.create("test-tool") output = fake_out.getvalue() @@ -82,7 +83,7 @@ def test_install_success(mock_get, mock_subprocess_run): capture_output=False, text=True, check=True, - env=unittest.mock.ANY + env=unittest.mock.ANY, ) assert "Successfully installed sample-tool" in output diff --git a/tests/crew_test.py b/tests/crew_test.py index 0cb8f469c..8354f6584 100644 --- a/tests/crew_test.py +++ b/tests/crew_test.py @@ -333,16 +333,16 @@ def test_manager_agent_delegating_to_assigned_task_agent(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Because we are mocking execute_sync, we never hit the underlying _execute_core # which sets the output attribute of the task task.output = mock_task_output - with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Verify execute_sync was called once @@ -350,12 +350,20 @@ def test_manager_agent_delegating_to_assigned_task_agent(): # Get the tools argument from the call _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] # Verify the delegation tools were passed correctly assert len(tools) == 2 - assert any("Delegate a specific task to one of the following coworkers: Researcher" in tool.description for tool in tools) - assert any("Ask a specific question to one of the following coworkers: Researcher" in tool.description for tool in tools) + assert any( + "Delegate a specific task to one of the following coworkers: Researcher" + in tool.description + for tool in tools + ) + assert any( + "Ask a specific question to one of the following coworkers: Researcher" + in tool.description + for tool in tools + ) @pytest.mark.vcr(filter_headers=["authorization"]) @@ -404,7 +412,7 @@ def test_manager_agent_delegates_with_varied_role_cases(): backstory="A researcher with spaces in role name", allow_delegation=False, ) - + writer_caps = Agent( role="SENIOR WRITER", # All caps goal="Write with caps in role", @@ -426,13 +434,13 @@ def test_manager_agent_delegates_with_varied_role_cases(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) task.output = mock_task_output - with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Verify execute_sync was called once @@ -440,20 +448,32 @@ def test_manager_agent_delegates_with_varied_role_cases(): # Get the tools argument from the call _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] # Verify the delegation tools were passed correctly and can handle case/whitespace variations assert len(tools) == 2 - + # Check delegation tool descriptions (should work despite case/whitespace differences) delegation_tool = tools[0] question_tool = tools[1] - - assert "Delegate a specific task to one of the following coworkers:" in delegation_tool.description - assert " Researcher " in delegation_tool.description or "SENIOR WRITER" in delegation_tool.description - - assert "Ask a specific question to one of the following coworkers:" in question_tool.description - assert " Researcher " in question_tool.description or "SENIOR WRITER" in question_tool.description + + assert ( + "Delegate a specific task to one of the following coworkers:" + in delegation_tool.description + ) + assert ( + " Researcher " in delegation_tool.description + or "SENIOR WRITER" in delegation_tool.description + ) + + assert ( + "Ask a specific question to one of the following coworkers:" + in question_tool.description + ) + assert ( + " Researcher " in question_tool.description + or "SENIOR WRITER" in question_tool.description + ) @pytest.mark.vcr(filter_headers=["authorization"]) @@ -479,6 +499,7 @@ def test_crew_with_delegating_agents(): == "In the rapidly evolving landscape of technology, AI agents have emerged as formidable tools, revolutionizing how we interact with data and automate tasks. These sophisticated systems leverage machine learning and natural language processing to perform a myriad of functions, from virtual personal assistants to complex decision-making companions in industries such as finance, healthcare, and education. By mimicking human intelligence, AI agents can analyze massive data sets at unparalleled speeds, enabling businesses to uncover valuable insights, enhance productivity, and elevate user experiences to unprecedented levels.\n\nOne of the most striking aspects of AI agents is their adaptability; they learn from their interactions and continuously improve their performance over time. This feature is particularly valuable in customer service where AI agents can address inquiries, resolve issues, and provide personalized recommendations without the limitations of human fatigue. Moreover, with intuitive interfaces, AI agents enhance user interactions, making technology more accessible and user-friendly, thereby breaking down barriers that have historically hindered digital engagement.\n\nDespite their immense potential, the deployment of AI agents raises important ethical and practical considerations. Issues related to privacy, data security, and the potential for job displacement necessitate thoughtful dialogue and proactive measures. Striking a balance between technological innovation and societal impact will be crucial as organizations integrate these agents into their operations. Additionally, ensuring transparency in AI decision-making processes is vital to maintain public trust as AI agents become an integral part of daily life.\n\nLooking ahead, the future of AI agents appears bright, with ongoing advancements promising even greater capabilities. As we continue to harness the power of AI, we can expect these agents to play a transformative role in shaping various sectorsโ€”streamlining workflows, enabling smarter decision-making, and fostering more personalized experiences. Embracing this technology responsibly can lead to a future where AI agents not only augment human effort but also inspire creativity and efficiency across the board, ultimately redefining our interaction with the digital world." ) + @pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_with_delegating_agents_should_not_override_task_tools(): from typing import Type @@ -489,6 +510,7 @@ def test_crew_with_delegating_agents_should_not_override_task_tools(): class TestToolInput(BaseModel): """Input schema for TestTool.""" + query: str = Field(..., description="Query to process") class TestTool(BaseTool): @@ -516,24 +538,29 @@ def test_crew_with_delegating_agents_should_not_override_task_tools(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Because we are mocking execute_sync, we never hit the underlying _execute_core # which sets the output attribute of the task tasks[0].output = mock_task_output - with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Execute the task and verify both tools are present _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] + + assert any( + isinstance(tool, TestTool) for tool in tools + ), "TestTool should be present" + assert any( + "delegate" in tool.name.lower() for tool in tools + ), "Delegation tool should be present" - assert any(isinstance(tool, TestTool) for tool in tools), "TestTool should be present" - assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present" @pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_with_delegating_agents_should_not_override_agent_tools(): @@ -545,6 +572,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools(): class TestToolInput(BaseModel): """Input schema for TestTool.""" + query: str = Field(..., description="Query to process") class TestTool(BaseTool): @@ -563,7 +591,7 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools(): Task( description="Produce and amazing 1 paragraph draft of an article about AI Agents.", expected_output="A 4 paragraph article about AI.", - agent=new_ceo + agent=new_ceo, ) ] @@ -574,24 +602,29 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Because we are mocking execute_sync, we never hit the underlying _execute_core # which sets the output attribute of the task tasks[0].output = mock_task_output - with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Execute the task and verify both tools are present _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] + + assert any( + isinstance(tool, TestTool) for tool in new_ceo.tools + ), "TestTool should be present" + assert any( + "delegate" in tool.name.lower() for tool in tools + ), "Delegation tool should be present" - assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), "TestTool should be present" - assert any("delegate" in tool.name.lower() for tool in tools), "Delegation tool should be present" @pytest.mark.vcr(filter_headers=["authorization"]) def test_task_tools_override_agent_tools(): @@ -603,6 +636,7 @@ def test_task_tools_override_agent_tools(): class TestToolInput(BaseModel): """Input schema for TestTool.""" + query: str = Field(..., description="Query to process") class TestTool(BaseTool): @@ -630,14 +664,10 @@ def test_task_tools_override_agent_tools(): description="Write a test task", expected_output="Test output", agent=new_researcher, - tools=[AnotherTestTool()] + tools=[AnotherTestTool()], ) - crew = Crew( - agents=[new_researcher], - tasks=[task], - process=Process.sequential - ) + crew = Crew(agents=[new_researcher], tasks=[task], process=Process.sequential) crew.kickoff() @@ -650,6 +680,7 @@ def test_task_tools_override_agent_tools(): assert len(new_researcher.tools) == 1 assert isinstance(new_researcher.tools[0], TestTool) + @pytest.mark.vcr(filter_headers=["authorization"]) def test_task_tools_override_agent_tools_with_allow_delegation(): """ @@ -702,13 +733,13 @@ def test_task_tools_override_agent_tools_with_allow_delegation(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # We mock execute_sync to verify which tools get used at runtime - with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Inspect the call kwargs to verify the actual tools passed to execution @@ -716,16 +747,23 @@ def test_task_tools_override_agent_tools_with_allow_delegation(): used_tools = kwargs["tools"] # Confirm AnotherTestTool is present but TestTool is not - assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), "AnotherTestTool should be present" - assert not any(isinstance(tool, TestTool) for tool in used_tools), "TestTool should not be present among used tools" + assert any( + isinstance(tool, AnotherTestTool) for tool in used_tools + ), "AnotherTestTool should be present" + assert not any( + isinstance(tool, TestTool) for tool in used_tools + ), "TestTool should not be present among used tools" # Confirm delegation tool(s) are present - assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present" + assert any( + "delegate" in tool.name.lower() for tool in used_tools + ), "Delegation tool should be present" # Finally, make sure the agent's original tools remain unchanged assert len(researcher_with_delegation.tools) == 1 assert isinstance(researcher_with_delegation.tools[0], TestTool) + @pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_verbose_output(capsys): tasks = [ @@ -1012,8 +1050,8 @@ def test_three_task_with_async_execution(): ) -@pytest.mark.vcr(filter_headers=["authorization"]) @pytest.mark.asyncio +@pytest.mark.vcr(filter_headers=["authorization"]) async def test_crew_async_kickoff(): inputs = [ {"topic": "dog"}, @@ -1060,8 +1098,9 @@ async def test_crew_async_kickoff(): assert result[0].token_usage.successful_requests > 0 # type: ignore +@pytest.mark.asyncio @pytest.mark.vcr(filter_headers=["authorization"]) -def test_async_task_execution_call_count(): +async def test_async_task_execution_call_count(): from unittest.mock import MagicMock, patch list_ideas = Task( @@ -1188,7 +1227,6 @@ def test_kickoff_for_each_empty_input(): assert results == [] -@pytest.mark.vcr(filter_headers=["authorization"]) def test_kickoff_for_each_invalid_input(): """Tests if kickoff_for_each raises TypeError for invalid input types.""" @@ -1211,7 +1249,6 @@ def test_kickoff_for_each_invalid_input(): crew.kickoff_for_each("invalid input") -@pytest.mark.vcr(filter_headers=["authorization"]) def test_kickoff_for_each_error_handling(): """Tests error handling in kickoff_for_each when kickoff raises an error.""" from unittest.mock import patch @@ -1248,7 +1285,6 @@ def test_kickoff_for_each_error_handling(): crew.kickoff_for_each(inputs=inputs) -@pytest.mark.vcr(filter_headers=["authorization"]) @pytest.mark.asyncio async def test_kickoff_async_basic_functionality_and_output(): """Tests the basic functionality and output of kickoff_async.""" @@ -1283,7 +1319,6 @@ async def test_kickoff_async_basic_functionality_and_output(): mock_kickoff.assert_called_once_with(inputs) -@pytest.mark.vcr(filter_headers=["authorization"]) @pytest.mark.asyncio async def test_async_kickoff_for_each_async_basic_functionality_and_output(): """Tests the basic functionality and output of kickoff_for_each_async.""" @@ -1330,7 +1365,6 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output(): mock_kickoff_async.assert_any_call(inputs=input_data) -@pytest.mark.vcr(filter_headers=["authorization"]) @pytest.mark.asyncio async def test_async_kickoff_for_each_async_empty_input(): """Tests if akickoff_for_each_async handles an empty input list.""" @@ -1514,12 +1548,12 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff(): crew = Crew(agents=[programmer], tasks=[task]) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) - with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Get the tools that were actually used in execution @@ -1528,7 +1562,10 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff(): # Verify that exactly one tool was used and it was a CodeInterpreterTool assert len(used_tools) == 1, "Should have exactly one tool" - assert isinstance(used_tools[0], CodeInterpreterTool), "Tool should be CodeInterpreterTool" + assert isinstance( + used_tools[0], CodeInterpreterTool + ), "Tool should be CodeInterpreterTool" + @pytest.mark.vcr(filter_headers=["authorization"]) def test_delegation_is_not_enabled_if_there_are_only_one_agent(): @@ -1639,16 +1676,16 @@ def test_hierarchical_crew_creation_tasks_with_agents(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Because we are mocking execute_sync, we never hit the underlying _execute_core # which sets the output attribute of the task task.output = mock_task_output - with patch.object(Task, 'execute_sync', return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Verify execute_sync was called once @@ -1656,12 +1693,20 @@ def test_hierarchical_crew_creation_tasks_with_agents(): # Get the tools argument from the call _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] # Verify the delegation tools were passed correctly assert len(tools) == 2 - assert any("Delegate a specific task to one of the following coworkers: Senior Writer" in tool.description for tool in tools) - assert any("Ask a specific question to one of the following coworkers: Senior Writer" in tool.description for tool in tools) + assert any( + "Delegate a specific task to one of the following coworkers: Senior Writer" + in tool.description + for tool in tools + ) + assert any( + "Ask a specific question to one of the following coworkers: Senior Writer" + in tool.description + for tool in tools + ) @pytest.mark.vcr(filter_headers=["authorization"]) @@ -1684,9 +1729,7 @@ def test_hierarchical_crew_creation_tasks_with_async_execution(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Create a mock Future that returns our TaskOutput @@ -1697,7 +1740,9 @@ def test_hierarchical_crew_creation_tasks_with_async_execution(): # which sets the output attribute of the task task.output = mock_task_output - with patch.object(Task, 'execute_async', return_value=mock_future) as mock_execute_async: + with patch.object( + Task, "execute_async", return_value=mock_future + ) as mock_execute_async: crew.kickoff() # Verify execute_async was called once @@ -1705,12 +1750,20 @@ def test_hierarchical_crew_creation_tasks_with_async_execution(): # Get the tools argument from the call _, kwargs = mock_execute_async.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] # Verify the delegation tools were passed correctly assert len(tools) == 2 - assert any("Delegate a specific task to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools) - assert any("Ask a specific question to one of the following coworkers: Senior Writer\n" in tool.description for tool in tools) + assert any( + "Delegate a specific task to one of the following coworkers: Senior Writer\n" + in tool.description + for tool in tools + ) + assert any( + "Ask a specific question to one of the following coworkers: Senior Writer\n" + in tool.description + for tool in tools + ) @pytest.mark.vcr(filter_headers=["authorization"]) @@ -2039,7 +2092,6 @@ def test_crew_output_file_end_to_end(tmp_path): assert expected_file.exists(), f"Output file {expected_file} was not created" -@pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_output_file_validation_failures(): """Test output file validation failures in a crew context.""" agent = Agent( @@ -2055,7 +2107,7 @@ def test_crew_output_file_validation_failures(): description="Analyze data", expected_output="Analysis results", agent=agent, - output_file="../output.txt" + output_file="../output.txt", ) Crew(agents=[agent], tasks=[task]).kickoff() @@ -2065,7 +2117,7 @@ def test_crew_output_file_validation_failures(): description="Analyze data", expected_output="Analysis results", agent=agent, - output_file="output.txt | rm -rf /" + output_file="output.txt | rm -rf /", ) Crew(agents=[agent], tasks=[task]).kickoff() @@ -2075,7 +2127,7 @@ def test_crew_output_file_validation_failures(): description="Analyze data", expected_output="Analysis results", agent=agent, - output_file="~/output.txt" + output_file="~/output.txt", ) Crew(agents=[agent], tasks=[task]).kickoff() @@ -2085,12 +2137,11 @@ def test_crew_output_file_validation_failures(): description="Analyze data", expected_output="Analysis results", agent=agent, - output_file="{invalid-name}/output.txt" + output_file="{invalid-name}/output.txt", ) Crew(agents=[agent], tasks=[task]).kickoff() -@pytest.mark.vcr(filter_headers=["authorization"]) def test_manager_agent(): from unittest.mock import patch @@ -3049,6 +3100,7 @@ def test_task_tools_preserve_code_execution_tools(): class TestToolInput(BaseModel): """Input schema for TestTool.""" + query: str = Field(..., description="Query to process") class TestTool(BaseTool): @@ -3082,7 +3134,7 @@ def test_task_tools_preserve_code_execution_tools(): description="Write a program to calculate fibonacci numbers.", expected_output="A working fibonacci calculator.", agent=programmer, - tools=[TestTool()] + tools=[TestTool()], ) crew = Crew( @@ -3092,12 +3144,12 @@ def test_task_tools_preserve_code_execution_tools(): ) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) - with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Get the tools that were actually used in execution @@ -3105,12 +3157,21 @@ def test_task_tools_preserve_code_execution_tools(): used_tools = kwargs["tools"] # Verify all expected tools are present - assert any(isinstance(tool, TestTool) for tool in used_tools), "Task's TestTool should be present" - assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), "CodeInterpreterTool should be present" - assert any("delegate" in tool.name.lower() for tool in used_tools), "Delegation tool should be present" + assert any( + isinstance(tool, TestTool) for tool in used_tools + ), "Task's TestTool should be present" + assert any( + isinstance(tool, CodeInterpreterTool) for tool in used_tools + ), "CodeInterpreterTool should be present" + assert any( + "delegate" in tool.name.lower() for tool in used_tools + ), "Delegation tool should be present" # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools) - assert len(used_tools) == 4, "Should have TestTool, CodeInterpreter, and 2 delegation tools" + assert ( + len(used_tools) == 4 + ), "Should have TestTool, CodeInterpreter, and 2 delegation tools" + @pytest.mark.vcr(filter_headers=["authorization"]) def test_multimodal_flag_adds_multimodal_tools(): @@ -3139,13 +3200,13 @@ def test_multimodal_flag_adds_multimodal_tools(): crew = Crew(agents=[multimodal_agent], tasks=[task], process=Process.sequential) mock_task_output = TaskOutput( - description="Mock description", - raw="mocked output", - agent="mocked agent" + description="Mock description", raw="mocked output", agent="mocked agent" ) # Mock execute_sync to verify the tools passed at runtime - with patch.object(Task, "execute_sync", return_value=mock_task_output) as mock_execute_sync: + with patch.object( + Task, "execute_sync", return_value=mock_task_output + ) as mock_execute_sync: crew.kickoff() # Get the tools that were actually used in execution @@ -3153,13 +3214,14 @@ def test_multimodal_flag_adds_multimodal_tools(): used_tools = kwargs["tools"] # Check that the multimodal tool was added - assert any(isinstance(tool, AddImageTool) for tool in used_tools), ( - "AddImageTool should be present when agent is multimodal" - ) + assert any( + isinstance(tool, AddImageTool) for tool in used_tools + ), "AddImageTool should be present when agent is multimodal" # Verify we have exactly one tool (just the AddImageTool) assert len(used_tools) == 1, "Should only have the AddImageTool" + @pytest.mark.vcr(filter_headers=["authorization"]) def test_multimodal_agent_image_tool_handling(): """ @@ -3201,10 +3263,10 @@ def test_multimodal_agent_image_tool_handling(): mock_task_output = TaskOutput( description="Mock description", raw="A detailed analysis of the image", - agent="Image Analyst" + agent="Image Analyst", ) - with patch.object(Task, 'execute_sync') as mock_execute_sync: + with patch.object(Task, "execute_sync") as mock_execute_sync: # Set up the mock to return our task output mock_execute_sync.return_value = mock_task_output @@ -3213,7 +3275,7 @@ def test_multimodal_agent_image_tool_handling(): # Get the tools that were passed to execute_sync _, kwargs = mock_execute_sync.call_args - tools = kwargs['tools'] + tools = kwargs["tools"] # Verify the AddImageTool is present and properly configured image_tools = [tool for tool in tools if tool.name == "Add image to content"] @@ -3223,7 +3285,7 @@ def test_multimodal_agent_image_tool_handling(): image_tool = image_tools[0] result = image_tool._run( image_url="https://example.com/test-image.jpg", - action="Please analyze this image" + action="Please analyze this image", ) # Verify the tool returns the expected format @@ -3233,6 +3295,7 @@ def test_multimodal_agent_image_tool_handling(): assert result["content"][0]["type"] == "text" assert result["content"][1]["type"] == "image_url" + @pytest.mark.vcr(filter_headers=["authorization"]) def test_multimodal_agent_live_image_analysis(): """ @@ -3246,7 +3309,7 @@ def test_multimodal_agent_live_image_analysis(): allow_delegation=False, multimodal=True, verbose=True, - llm="gpt-4o" + llm="gpt-4o", ) # Create a task for image analysis @@ -3257,19 +3320,18 @@ def test_multimodal_agent_live_image_analysis(): Image: {image_url} """, expected_output="A comprehensive description of the image contents.", - agent=image_analyst + agent=image_analyst, ) # Create and run the crew - crew = Crew( - agents=[image_analyst], - tasks=[analyze_image] - ) + crew = Crew(agents=[image_analyst], tasks=[analyze_image]) # Execute with an image URL - result = crew.kickoff(inputs={ - "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=" - }) + result = crew.kickoff( + inputs={ + "image_url": "https://media.istockphoto.com/id/946087016/photo/aerial-view-of-lower-manhattan-new-york.jpg?s=612x612&w=0&k=20&c=viLiMRznQ8v5LzKTt_LvtfPFUVl1oiyiemVdSlm29_k=" + } + ) # Verify we got a meaningful response assert isinstance(result.raw, str) diff --git a/tests/knowledge/knowledge_test.py b/tests/knowledge/knowledge_test.py index 6704d3031..fad2d2513 100644 --- a/tests/knowledge/knowledge_test.py +++ b/tests/knowledge/knowledge_test.py @@ -578,14 +578,6 @@ def test_multiple_docling_sources(): assert docling_source.content is not None -def test_docling_source_with_local_file(): - current_dir = Path(__file__).parent - pdf_path = current_dir / "crewai_quickstart.pdf" - docling_source = CrewDoclingSource(file_paths=[pdf_path]) - assert docling_source.file_paths == [pdf_path] - assert docling_source.content is not None - - def test_file_path_validation(): """Test file path validation for knowledge sources.""" current_dir = Path(__file__).parent @@ -606,6 +598,6 @@ def test_file_path_validation(): # Test neither file_path nor file_paths provided with pytest.raises( ValueError, - match="file_path/file_paths must be a Path, str, or a list of these types" + match="file_path/file_paths must be a Path, str, or a list of these types", ): PDFKnowledgeSource() diff --git a/tests/task_test.py b/tests/task_test.py index dc15c251f..0fcb499b2 100644 --- a/tests/task_test.py +++ b/tests/task_test.py @@ -719,7 +719,7 @@ def test_interpolate_inputs(): task = Task( description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.", expected_output="Bullet point list of 5 interesting ideas about {topic}.", - output_file="/tmp/{topic}/output_{date}.txt" + output_file="/tmp/{topic}/output_{date}.txt", ) task.interpolate_inputs(inputs={"topic": "AI", "date": "2024"}) @@ -742,41 +742,35 @@ def test_interpolate_inputs(): def test_interpolate_only(): """Test the interpolate_only method for various scenarios including JSON structure preservation.""" task = Task( - description="Unused in this test", - expected_output="Unused in this test" + description="Unused in this test", expected_output="Unused in this test" ) - + # Test JSON structure preservation json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}' result = task.interpolate_only( input_string=json_string, - inputs={"placeholder": "the data", "nestedVal": "something else"} + inputs={"placeholder": "the data", "nestedVal": "something else"}, ) assert '"info": "Look at the data"' in result assert '"val": "something else"' in result assert "{placeholder}" not in result assert "{nestedVal}" not in result - + # Test normal string interpolation normal_string = "Hello {name}, welcome to {place}!" result = task.interpolate_only( - input_string=normal_string, - inputs={"name": "John", "place": "CrewAI"} + input_string=normal_string, inputs={"name": "John", "place": "CrewAI"} ) assert result == "Hello John, welcome to CrewAI!" - + # Test empty string - result = task.interpolate_only( - input_string="", - inputs={"unused": "value"} - ) + result = task.interpolate_only(input_string="", inputs={"unused": "value"}) assert result == "" - + # Test string with no placeholders no_placeholders = "Hello, this is a test" result = task.interpolate_only( - input_string=no_placeholders, - inputs={"unused": "value"} + input_string=no_placeholders, inputs={"unused": "value"} ) assert result == no_placeholders @@ -880,56 +874,65 @@ def test_key(): def test_output_file_validation(): """Test output file path validation.""" # Valid paths - assert Task( - description="Test task", - expected_output="Test output", - output_file="output.txt" - ).output_file == "output.txt" - assert Task( - description="Test task", - expected_output="Test output", - output_file="/tmp/output.txt" - ).output_file == "tmp/output.txt" - assert Task( - description="Test task", - expected_output="Test output", - output_file="{dir}/output_{date}.txt" - ).output_file == "{dir}/output_{date}.txt" - + assert ( + Task( + description="Test task", + expected_output="Test output", + output_file="output.txt", + ).output_file + == "output.txt" + ) + assert ( + Task( + description="Test task", + expected_output="Test output", + output_file="/tmp/output.txt", + ).output_file + == "tmp/output.txt" + ) + assert ( + Task( + description="Test task", + expected_output="Test output", + output_file="{dir}/output_{date}.txt", + ).output_file + == "{dir}/output_{date}.txt" + ) + # Invalid paths with pytest.raises(ValueError, match="Path traversal"): Task( description="Test task", expected_output="Test output", - output_file="../output.txt" + output_file="../output.txt", ) with pytest.raises(ValueError, match="Path traversal"): Task( description="Test task", expected_output="Test output", - output_file="folder/../output.txt" + output_file="folder/../output.txt", ) with pytest.raises(ValueError, match="Shell special characters"): Task( description="Test task", expected_output="Test output", - output_file="output.txt | rm -rf /" + output_file="output.txt | rm -rf /", ) with pytest.raises(ValueError, match="Shell expansion"): Task( description="Test task", expected_output="Test output", - output_file="~/output.txt" + output_file="~/output.txt", ) with pytest.raises(ValueError, match="Shell expansion"): Task( description="Test task", expected_output="Test output", - output_file="$HOME/output.txt" + output_file="$HOME/output.txt", ) with pytest.raises(ValueError, match="Invalid template variable"): Task( description="Test task", expected_output="Test output", - output_file="{invalid-name}/output.txt" + output_file="{invalid-name}/output.txt", ) diff --git a/tests/test_manager_llm_delegation.py b/tests/test_manager_llm_delegation.py index d1f2068e4..6f8671255 100644 --- a/tests/test_manager_llm_delegation.py +++ b/tests/test_manager_llm_delegation.py @@ -8,48 +8,49 @@ from crewai.tools.agent_tools.base_agent_tools import BaseAgentTool class TestAgentTool(BaseAgentTool): """Concrete implementation of BaseAgentTool for testing.""" + def _run(self, *args, **kwargs): """Implement required _run method.""" return "Test response" -@pytest.mark.parametrize("role_name,should_match", [ - ('Futel Official Infopoint', True), # exact match - (' "Futel Official Infopoint" ', True), # extra quotes and spaces - ('Futel Official Infopoint\n', True), # trailing newline - ('"Futel Official Infopoint"', True), # embedded quotes - (' FUTEL\nOFFICIAL INFOPOINT ', True), # multiple whitespace and newline - ('futel official infopoint', True), # lowercase - ('FUTEL OFFICIAL INFOPOINT', True), # uppercase - ('Non Existent Agent', False), # non-existent agent - (None, False), # None agent name -]) + +@pytest.mark.parametrize( + "role_name,should_match", + [ + ("Futel Official Infopoint", True), # exact match + (' "Futel Official Infopoint" ', True), # extra quotes and spaces + ("Futel Official Infopoint\n", True), # trailing newline + ('"Futel Official Infopoint"', True), # embedded quotes + (" FUTEL\nOFFICIAL INFOPOINT ", True), # multiple whitespace and newline + ("futel official infopoint", True), # lowercase + ("FUTEL OFFICIAL INFOPOINT", True), # uppercase + ("Non Existent Agent", False), # non-existent agent + (None, False), # None agent name + ], +) def test_agent_tool_role_matching(role_name, should_match): """Test that agent tools can match roles regardless of case, whitespace, and special characters.""" # Create test agent test_agent = Agent( - role='Futel Official Infopoint', - goal='Answer questions about Futel', - backstory='Futel Football Club info', - allow_delegation=False + role="Futel Official Infopoint", + goal="Answer questions about Futel", + backstory="Futel Football Club info", + allow_delegation=False, ) # Create test agent tool agent_tool = TestAgentTool( - name="test_tool", - description="Test tool", - agents=[test_agent] + name="test_tool", description="Test tool", agents=[test_agent] ) # Test role matching - result = agent_tool._execute( - agent_name=role_name, - task='Test task', - context=None - ) + result = agent_tool._execute(agent_name=role_name, task="Test task", context=None) if should_match: - assert "coworker mentioned not found" not in result.lower(), \ - f"Should find agent with role name: {role_name}" + assert ( + "coworker mentioned not found" not in result.lower() + ), f"Should find agent with role name: {role_name}" else: - assert "coworker mentioned not found" in result.lower(), \ - f"Should not find agent with role name: {role_name}" + assert ( + "coworker mentioned not found" in result.lower() + ), f"Should not find agent with role name: {role_name}" diff --git a/tests/test_task_guardrails.py b/tests/test_task_guardrails.py index dc96cb878..e22e76234 100644 --- a/tests/test_task_guardrails.py +++ b/tests/test_task_guardrails.py @@ -15,10 +15,7 @@ def test_task_without_guardrail(): agent.execute_task.return_value = "test result" agent.crew = None - task = Task( - description="Test task", - expected_output="Output" - ) + task = Task(description="Test task", expected_output="Output") result = task.execute_sync(agent=agent) assert isinstance(result, TaskOutput) @@ -27,6 +24,7 @@ def test_task_without_guardrail(): def test_task_with_successful_guardrail(): """Test that successful guardrail validation passes transformed result.""" + def guardrail(result: TaskOutput): return (True, result.raw.upper()) @@ -35,11 +33,7 @@ def test_task_with_successful_guardrail(): agent.execute_task.return_value = "test result" agent.crew = None - task = Task( - description="Test task", - expected_output="Output", - guardrail=guardrail - ) + task = Task(description="Test task", expected_output="Output", guardrail=guardrail) result = task.execute_sync(agent=agent) assert isinstance(result, TaskOutput) @@ -48,22 +42,20 @@ def test_task_with_successful_guardrail(): def test_task_with_failing_guardrail(): """Test that failing guardrail triggers retry with error context.""" + def guardrail(result: TaskOutput): return (False, "Invalid format") agent = Mock() agent.role = "test_agent" - agent.execute_task.side_effect = [ - "bad result", - "good result" - ] + agent.execute_task.side_effect = ["bad result", "good result"] agent.crew = None task = Task( description="Test task", expected_output="Output", guardrail=guardrail, - max_retries=1 + max_retries=1, ) # First execution fails guardrail, second succeeds @@ -77,6 +69,7 @@ def test_task_with_failing_guardrail(): def test_task_with_guardrail_retries(): """Test that guardrail respects max_retries configuration.""" + def guardrail(result: TaskOutput): return (False, "Invalid format") @@ -89,7 +82,7 @@ def test_task_with_guardrail_retries(): description="Test task", expected_output="Output", guardrail=guardrail, - max_retries=2 + max_retries=2, ) with pytest.raises(Exception) as exc_info: @@ -102,6 +95,7 @@ def test_task_with_guardrail_retries(): def test_guardrail_error_in_context(): """Test that guardrail error is passed in context for retry.""" + def guardrail(result: TaskOutput): return (False, "Expected JSON, got string") @@ -113,11 +107,12 @@ def test_guardrail_error_in_context(): description="Test task", expected_output="Output", guardrail=guardrail, - max_retries=1 + max_retries=1, ) # Mock execute_task to succeed on second attempt first_call = True + def execute_task(task, context, tools): nonlocal first_call if first_call: diff --git a/uv.lock b/uv.lock index c37a1fa4e..0e3e63276 100644 --- a/uv.lock +++ b/uv.lock @@ -1,10 +1,18 @@ version = 1 requires-python = ">=3.10, <3.13" resolution-markers = [ - "python_full_version < '3.11'", - "python_full_version == '3.11.*'", - "python_full_version >= '3.12' and python_full_version < '3.12.4'", - "python_full_version >= '3.12.4'", + "python_full_version < '3.11' and sys_platform == 'darwin'", + "python_full_version < '3.11' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version < '3.11' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version < '3.11' and sys_platform != 'darwin' and sys_platform != 'linux')", + "python_full_version == '3.11.*' and sys_platform == 'darwin'", + "python_full_version == '3.11.*' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version == '3.11.*' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version == '3.11.*' and sys_platform != 'darwin' and sys_platform != 'linux')", + "python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform == 'darwin'", + "python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version >= '3.12' and python_full_version < '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12' and python_full_version < '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')", + "python_full_version >= '3.12.4' and sys_platform == 'darwin'", + "python_full_version >= '3.12.4' and platform_machine == 'aarch64' and sys_platform == 'linux'", + "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and sys_platform == 'linux') or (python_full_version >= '3.12.4' and sys_platform != 'darwin' and sys_platform != 'linux')", ] [[package]] @@ -620,6 +628,9 @@ agentops = [ docling = [ { name = "docling" }, ] +embeddings = [ + { name = "tiktoken" }, +] fastembed = [ { name = "fastembed" }, ] @@ -642,7 +653,6 @@ tools = [ [package.dev-dependencies] dev = [ { name = "cairosvg" }, - { name = "crewai-tools" }, { name = "mkdocs" }, { name = "mkdocs-material" }, { name = "mkdocs-material-extensions" }, @@ -688,6 +698,7 @@ requires-dist = [ { name = "python-dotenv", specifier = ">=1.0.0" }, { name = "pyvis", specifier = ">=0.3.2" }, { name = "regex", specifier = ">=2024.9.11" }, + { name = "tiktoken", marker = "extra == 'embeddings'", specifier = "~=0.7.0" }, { name = "tomli", specifier = ">=2.0.2" }, { name = "tomli-w", specifier = ">=1.1.0" }, { name = "uv", specifier = ">=0.4.25" }, @@ -696,7 +707,6 @@ requires-dist = [ [package.metadata.requires-dev] dev = [ { name = "cairosvg", specifier = ">=2.7.1" }, - { name = "crewai-tools", specifier = ">=0.17.0" }, { name = "mkdocs", specifier = ">=1.4.3" }, { name = "mkdocs-material", specifier = ">=9.5.7" }, { name = "mkdocs-material-extensions", specifier = ">=1.3.1" }, @@ -2890,7 +2900,7 @@ name = "nvidia-cudnn-cu12" version = "9.1.0.70" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/9f/fd/713452cd72343f682b1c7b9321e23829f00b842ceaedcda96e742ea0b0b3/nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl", hash = "sha256:165764f44ef8c61fcdfdfdbe769d687e06374059fbb388b6c89ecb0e28793a6f", size = 664752741 }, @@ -2917,9 +2927,9 @@ name = "nvidia-cusolver-cu12" version = "11.4.5.107" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, - { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, - { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, + { name = "nvidia-cublas-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, + { name = "nvidia-cusparse-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/bc/1d/8de1e5c67099015c834315e333911273a8c6aaba78923dd1d1e25fc5f217/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd", size = 124161928 }, @@ -2930,7 +2940,7 @@ name = "nvidia-cusparse-cu12" version = "12.1.0.106" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, + { name = "nvidia-nvjitlink-cu12", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/65/5b/cfaeebf25cd9fdec14338ccb16f6b2c4c7fa9163aefcf057d86b9cc248bb/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c", size = 195958278 }, @@ -5155,7 +5165,7 @@ name = "triton" version = "3.0.0" source = { registry = "https://pypi.org/simple" } dependencies = [ - { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux')" }, + { name = "filelock", marker = "(platform_machine != 'aarch64' and platform_system != 'Darwin') or (platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'linux')" }, ] wheels = [ { url = "https://files.pythonhosted.org/packages/45/27/14cc3101409b9b4b9241d2ba7deaa93535a217a211c86c4cc7151fb12181/triton-3.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e1efef76935b2febc365bfadf74bcb65a6f959a9872e5bddf44cc9e0adce1e1a", size = 209376304 },