| | --- |
| | language: |
| | - en |
| | license: apache-2.0 |
| | tags: |
| | - sentence-transformers |
| | - sentence-similarity |
| | - feature-extraction |
| | - dense |
| | - generated_from_trainer |
| | - dataset_size:900 |
| | - loss:MatryoshkaLoss |
| | - loss:MultipleNegativesRankingLoss |
| | base_model: microsoft/codebert-base |
| | widget: |
| | - source_sentence: Explain the test_code_docs_search_tool logic |
| | sentences: |
| | - "def test_anthropic_call_with_interceptor_tracks_requests(self) -> None:\n \ |
| | \ \"\"\"Test that interceptor tracks Anthropic API requests.\"\"\"\n \ |
| | \ interceptor = AnthropicTestInterceptor()\n llm = LLM(model=\"anthropic/claude-3-5-haiku-20241022\"\ |
| | , interceptor=interceptor)\n\n # Make a simple completion call\n \ |
| | \ result = llm.call(\n messages=[{\"role\": \"user\", \"content\"\ |
| | : \"Say 'Hello World' and nothing else\"}]\n )\n\n # Verify custom\ |
| | \ headers were added\n for request in interceptor.outbound_calls:\n \ |
| | \ assert \"X-Anthropic-Interceptor\" in request.headers\n assert\ |
| | \ request.headers[\"X-Anthropic-Interceptor\"] == \"anthropic-test-value\"\n \ |
| | \ assert \"X-Request-ID\" in request.headers\n assert request.headers[\"\ |
| | X-Request-ID\"] == \"test-request-456\"\n\n # Verify response was tracked\n\ |
| | \ for response in interceptor.inbound_calls:\n assert \"X-Response-Tracked\"\ |
| | \ in response.headers\n assert response.headers[\"X-Response-Tracked\"\ |
| | ] == \"true\"\n\n # Verify result is valid\n assert result is not\ |
| | \ None\n assert isinstance(result, str)\n assert len(result) > 0" |
| | - "def on_inbound(self, message: httpx.Response) -> httpx.Response:\n \"\"\ |
| | \"Pass through inbound response.\n\n Args:\n message: The inbound\ |
| | \ response.\n\n Returns:\n The response unchanged.\n \ |
| | \ \"\"\"\n return message" |
| | - "def test_code_docs_search_tool(mock_adapter):\n mock_adapter.query.return_value\ |
| | \ = \"test documentation\"\n\n docs_url = \"https://crewai.com/any-docs-url\"\ |
| | \n search_query = \"test documentation\"\n tool = CodeDocsSearchTool(docs_url=docs_url,\ |
| | \ adapter=mock_adapter)\n result = tool._run(search_query=search_query)\n \ |
| | \ assert \"test documentation\" in result\n mock_adapter.add.assert_called_once_with(docs_url,\ |
| | \ data_type=DataType.DOCS_SITE)\n mock_adapter.query.assert_called_once_with(\n\ |
| | \ search_query, similarity_threshold=0.6, limit=5\n )\n\n mock_adapter.query.reset_mock()\n\ |
| | \ mock_adapter.add.reset_mock()\n\n tool = CodeDocsSearchTool(adapter=mock_adapter)\n\ |
| | \ result = tool._run(docs_url=docs_url, search_query=search_query)\n assert\ |
| | \ \"test documentation\" in result\n mock_adapter.add.assert_called_once_with(docs_url,\ |
| | \ data_type=DataType.DOCS_SITE)\n mock_adapter.query.assert_called_once_with(\n\ |
| | \ search_query, similarity_threshold=0.6, limit=5\n )" |
| | - source_sentence: Explain the test_openai_get_client_params_with_base_url_priority |
| | logic |
| | sentences: |
| | - "def test_openai_get_client_params_with_base_url_priority():\n \"\"\"\n \ |
| | \ Test that base_url takes priority over api_base in _get_client_params\n \"\ |
| | \"\"\n llm = OpenAICompletion(\n model=\"gpt-4o\",\n base_url=\"\ |
| | https://priority.openai.com/v1\",\n api_base=\"https://fallback.openai.com/v1\"\ |
| | ,\n )\n client_params = llm._get_client_params()\n assert client_params[\"\ |
| | base_url\"] == \"https://priority.openai.com/v1\"" |
| | - "def get_context_window_size(self) -> int:\n \"\"\"Get the context window\ |
| | \ size for the LLM.\n\n Returns:\n The number of tokens/characters\ |
| | \ the model can handle.\n \"\"\"\n # Default implementation - subclasses\ |
| | \ should override with model-specific values\n return DEFAULT_CONTEXT_WINDOW_SIZE" |
| | - "def _inject_date_to_task(self, task: Task) -> None:\n \"\"\"Inject the\ |
| | \ current date into the task description if inject_date is enabled.\"\"\"\n \ |
| | \ if self.inject_date:\n from datetime import datetime\n\n \ |
| | \ try:\n valid_format_codes = [\n \"\ |
| | %Y\",\n \"%m\",\n \"%d\",\n \ |
| | \ \"%H\",\n \"%M\",\n \"%S\",\n \ |
| | \ \"%B\",\n \"%b\",\n \ |
| | \ \"%A\",\n \"%a\",\n ]\n is_valid\ |
| | \ = any(code in self.date_format for code in valid_format_codes)\n\n \ |
| | \ if not is_valid:\n raise ValueError(f\"Invalid date\ |
| | \ format: {self.date_format}\")\n\n current_date = datetime.now().strftime(self.date_format)\n\ |
| | \ task.description += f\"\\n\\nCurrent Date: {current_date}\"\n\ |
| | \ except Exception as e:\n self._logger.log(\"warning\"\ |
| | , f\"Failed to inject date: {e!s}\")" |
| | - source_sentence: How to implement async _get_connection? |
| | sentences: |
| | - "def mock_env():\n with patch.dict(os.environ, {\"CREWAI_PERSONAL_ACCESS_TOKEN\"\ |
| | : \"test_token\"}):\n os.environ.pop(\"CREWAI_PLUS_URL\", None)\n \ |
| | \ yield" |
| | - "async def _get_connection(self) -> SnowflakeConnection:\n \"\"\"Get a\ |
| | \ connection from the pool or create a new one.\"\"\"\n if self._pool_lock\ |
| | \ is None:\n raise RuntimeError(\"Pool lock not initialized\")\n \ |
| | \ if self._connection_pool is None:\n raise RuntimeError(\"Connection\ |
| | \ pool not initialized\")\n async with self._pool_lock:\n if\ |
| | \ not self._connection_pool:\n conn = await asyncio.get_event_loop().run_in_executor(\n\ |
| | \ self._thread_pool, self._create_connection\n \ |
| | \ )\n self._connection_pool.append(conn)\n return\ |
| | \ self._connection_pool.pop()" |
| | - "async def _arun(self, selector: str, thread_id: str = \"default\", **kwargs)\ |
| | \ -> str:\n \"\"\"Use the async tool.\"\"\"\n try:\n \ |
| | \ # Get the current page\n page = await self.get_async_page(thread_id)\n\ |
| | \n # Click on the element\n selector_effective = self._selector_effective(selector=selector)\n\ |
| | \ from playwright.async_api import TimeoutError as PlaywrightTimeoutError\n\ |
| | \n try:\n await page.click(\n selector_effective,\n\ |
| | \ strict=self.playwright_strict,\n timeout=self.playwright_timeout,\n\ |
| | \ )\n except PlaywrightTimeoutError:\n \ |
| | \ return f\"Unable to click on element '{selector}'\"\n except Exception\ |
| | \ as click_error:\n return f\"Unable to click on element '{selector}':\ |
| | \ {click_error!s}\"\n\n return f\"Clicked element '{selector}'\"\n\ |
| | \ except Exception as e:\n return f\"Error clicking on element:\ |
| | \ {e!s}\"" |
| | - source_sentence: Example usage of test_personal_access_token_from_environment |
| | sentences: |
| | - "async def close(self):\n return None" |
| | - "def test_structured_state_persistence(tmp_path):\n \"\"\"Test persistence\ |
| | \ with Pydantic model state.\"\"\"\n db_path = os.path.join(tmp_path, \"test_flows.db\"\ |
| | )\n persistence = SQLiteFlowPersistence(db_path)\n\n class StructuredFlow(Flow[TestState]):\n\ |
| | \ initial_state = TestState\n\n @start()\n @persist(persistence)\n\ |
| | \ def count_up(self):\n self.state.counter += 1\n \ |
| | \ self.state.message = f\"Count is {self.state.counter}\"\n\n # Run flow and\ |
| | \ verify state changes are saved\n flow = StructuredFlow(persistence=persistence)\n\ |
| | \ flow.kickoff()\n\n # Load and verify state\n saved_state = persistence.load_state(flow.state.id)\n\ |
| | \ assert saved_state is not None\n assert saved_state[\"counter\"] == 1\n\ |
| | \ assert saved_state[\"message\"] == \"Count is 1\"" |
| | - "def test_personal_access_token_from_environment(tool):\n assert tool.personal_access_token\ |
| | \ == \"test_token\"" |
| | - source_sentence: Best practices for handle_a2a_polling_started |
| | sentences: |
| | - "def external_supported_storages() -> dict[str, Any]:\n return {\n \ |
| | \ \"mem0\": ExternalMemory._configure_mem0,\n }" |
| | - "def handle_a2a_polling_started(\n self,\n task_id: str,\n \ |
| | \ polling_interval: float,\n endpoint: str,\n ) -> None:\n \ |
| | \ \"\"\"Handle A2A polling started event with panel display.\"\"\"\n content\ |
| | \ = Text()\n content.append(\"A2A Polling Started\\n\", style=\"cyan bold\"\ |
| | )\n content.append(\"Task ID: \", style=\"white\")\n content.append(f\"\ |
| | {task_id[:8]}...\\n\", style=\"cyan\")\n content.append(\"Interval: \"\ |
| | , style=\"white\")\n content.append(f\"{polling_interval}s\\n\", style=\"\ |
| | cyan\")\n\n self.print_panel(content, \"⏳ A2A Polling\", \"cyan\")" |
| | - "def test_agent_with_knowledge_sources_generate_search_query():\n content =\ |
| | \ \"Brandon's favorite color is red and he likes Mexican food.\"\n string_source\ |
| | \ = StringKnowledgeSource(content=content)\n\n with (\n patch(\"crewai.knowledge\"\ |
| | ) as mock_knowledge,\n patch(\n \"crewai.knowledge.storage.knowledge_storage.KnowledgeStorage\"\ |
| | \n ) as mock_knowledge_storage,\n patch(\n \"crewai.knowledge.source.base_knowledge_source.KnowledgeStorage\"\ |
| | \n ) as mock_base_knowledge_storage,\n patch(\"crewai.rag.chromadb.client.ChromaDBClient\"\ |
| | ) as mock_chromadb,\n ):\n mock_knowledge_instance = mock_knowledge.return_value\n\ |
| | \ mock_knowledge_instance.sources = [string_source]\n mock_knowledge_instance.query.return_value\ |
| | \ = [{\"content\": content}]\n\n mock_storage_instance = mock_knowledge_storage.return_value\n\ |
| | \ mock_storage_instance.sources = [string_source]\n mock_storage_instance.query.return_value\ |
| | \ = [{\"content\": content}]\n mock_storage_instance.save.return_value\ |
| | \ = None\n\n mock_chromadb_instance = mock_chromadb.return_value\n \ |
| | \ mock_chromadb_instance.add_documents.return_value = None\n\n mock_base_knowledge_storage.return_value\ |
| | \ = mock_storage_instance\n\n agent = Agent(\n role=\"Information\ |
| | \ Agent with extensive role description that is longer than 80 characters\",\n\ |
| | \ goal=\"Provide information based on knowledge sources\",\n \ |
| | \ backstory=\"You have access to specific knowledge sources.\",\n \ |
| | \ llm=LLM(model=\"gpt-4o-mini\"),\n knowledge_sources=[string_source],\n\ |
| | \ )\n\n task = Task(\n description=\"What is Brandon's\ |
| | \ favorite color?\",\n expected_output=\"The answer to the question,\ |
| | \ in a format like this: `{{name: str, favorite_color: str}}`\",\n \ |
| | \ agent=agent,\n )\n\n crew = Crew(agents=[agent], tasks=[task])\n\ |
| | \ result = crew.kickoff()\n\n # Updated assertion to check the JSON\ |
| | \ content\n assert \"Brandon\" in str(agent.knowledge_search_query)\n \ |
| | \ assert \"favorite color\" in str(agent.knowledge_search_query)\n\n \ |
| | \ assert \"red\" in result.raw.lower()" |
| | pipeline_tag: sentence-similarity |
| | library_name: sentence-transformers |
| | metrics: |
| | - cosine_accuracy@1 |
| | - cosine_accuracy@3 |
| | - cosine_accuracy@5 |
| | - cosine_accuracy@10 |
| | - cosine_precision@1 |
| | - cosine_precision@3 |
| | - cosine_precision@5 |
| | - cosine_precision@10 |
| | - cosine_recall@1 |
| | - cosine_recall@3 |
| | - cosine_recall@5 |
| | - cosine_recall@10 |
| | - cosine_ndcg@10 |
| | - cosine_mrr@10 |
| | - cosine_map@100 |
| | model-index: |
| | - name: CodeBERT Fine-tuned on CrewAI |
| | results: |
| | - task: |
| | type: information-retrieval |
| | name: Information Retrieval |
| | dataset: |
| | name: dim 768 |
| | type: dim_768 |
| | metrics: |
| | - type: cosine_accuracy@1 |
| | value: 0.57 |
| | name: Cosine Accuracy@1 |
| | - type: cosine_accuracy@3 |
| | value: 0.57 |
| | name: Cosine Accuracy@3 |
| | - type: cosine_accuracy@5 |
| | value: 0.57 |
| | name: Cosine Accuracy@5 |
| | - type: cosine_accuracy@10 |
| | value: 0.65 |
| | name: Cosine Accuracy@10 |
| | - type: cosine_precision@1 |
| | value: 0.57 |
| | name: Cosine Precision@1 |
| | - type: cosine_precision@3 |
| | value: 0.57 |
| | name: Cosine Precision@3 |
| | - type: cosine_precision@5 |
| | value: 0.57 |
| | name: Cosine Precision@5 |
| | - type: cosine_precision@10 |
| | value: 0.325 |
| | name: Cosine Precision@10 |
| | - type: cosine_recall@1 |
| | value: 0.11399999999999996 |
| | name: Cosine Recall@1 |
| | - type: cosine_recall@3 |
| | value: 0.3420000000000001 |
| | name: Cosine Recall@3 |
| | - type: cosine_recall@5 |
| | value: 0.57 |
| | name: Cosine Recall@5 |
| | - type: cosine_recall@10 |
| | value: 0.65 |
| | name: Cosine Recall@10 |
| | - type: cosine_ndcg@10 |
| | value: 0.6132795614223119 |
| | name: Cosine Ndcg@10 |
| | - type: cosine_mrr@10 |
| | value: 0.5833333333333334 |
| | name: Cosine Mrr@10 |
| | - type: cosine_map@100 |
| | value: 0.6323349876959563 |
| | name: Cosine Map@100 |
| | - task: |
| | type: information-retrieval |
| | name: Information Retrieval |
| | dataset: |
| | name: dim 512 |
| | type: dim_512 |
| | metrics: |
| | - type: cosine_accuracy@1 |
| | value: 0.56 |
| | name: Cosine Accuracy@1 |
| | - type: cosine_accuracy@3 |
| | value: 0.56 |
| | name: Cosine Accuracy@3 |
| | - type: cosine_accuracy@5 |
| | value: 0.56 |
| | name: Cosine Accuracy@5 |
| | - type: cosine_accuracy@10 |
| | value: 0.68 |
| | name: Cosine Accuracy@10 |
| | - type: cosine_precision@1 |
| | value: 0.56 |
| | name: Cosine Precision@1 |
| | - type: cosine_precision@3 |
| | value: 0.56 |
| | name: Cosine Precision@3 |
| | - type: cosine_precision@5 |
| | value: 0.56 |
| | name: Cosine Precision@5 |
| | - type: cosine_precision@10 |
| | value: 0.34 |
| | name: Cosine Precision@10 |
| | - type: cosine_recall@1 |
| | value: 0.11199999999999999 |
| | name: Cosine Recall@1 |
| | - type: cosine_recall@3 |
| | value: 0.336 |
| | name: Cosine Recall@3 |
| | - type: cosine_recall@5 |
| | value: 0.56 |
| | name: Cosine Recall@5 |
| | - type: cosine_recall@10 |
| | value: 0.68 |
| | name: Cosine Recall@10 |
| | - type: cosine_ndcg@10 |
| | value: 0.6249193421334678 |
| | name: Cosine Ndcg@10 |
| | - type: cosine_mrr@10 |
| | value: 0.5799999999999998 |
| | name: Cosine Mrr@10 |
| | - type: cosine_map@100 |
| | value: 0.6328444860345127 |
| | name: Cosine Map@100 |
| | - task: |
| | type: information-retrieval |
| | name: Information Retrieval |
| | dataset: |
| | name: dim 256 |
| | type: dim_256 |
| | metrics: |
| | - type: cosine_accuracy@1 |
| | value: 0.54 |
| | name: Cosine Accuracy@1 |
| | - type: cosine_accuracy@3 |
| | value: 0.54 |
| | name: Cosine Accuracy@3 |
| | - type: cosine_accuracy@5 |
| | value: 0.54 |
| | name: Cosine Accuracy@5 |
| | - type: cosine_accuracy@10 |
| | value: 0.67 |
| | name: Cosine Accuracy@10 |
| | - type: cosine_precision@1 |
| | value: 0.54 |
| | name: Cosine Precision@1 |
| | - type: cosine_precision@3 |
| | value: 0.54 |
| | name: Cosine Precision@3 |
| | - type: cosine_precision@5 |
| | value: 0.54 |
| | name: Cosine Precision@5 |
| | - type: cosine_precision@10 |
| | value: 0.335 |
| | name: Cosine Precision@10 |
| | - type: cosine_recall@1 |
| | value: 0.10799999999999997 |
| | name: Cosine Recall@1 |
| | - type: cosine_recall@3 |
| | value: 0.324 |
| | name: Cosine Recall@3 |
| | - type: cosine_recall@5 |
| | value: 0.54 |
| | name: Cosine Recall@5 |
| | - type: cosine_recall@10 |
| | value: 0.67 |
| | name: Cosine Recall@10 |
| | - type: cosine_ndcg@10 |
| | value: 0.6103292873112568 |
| | name: Cosine Ndcg@10 |
| | - type: cosine_mrr@10 |
| | value: 0.5616666666666664 |
| | name: Cosine Mrr@10 |
| | - type: cosine_map@100 |
| | value: 0.622676615058847 |
| | name: Cosine Map@100 |
| | - task: |
| | type: information-retrieval |
| | name: Information Retrieval |
| | dataset: |
| | name: dim 128 |
| | type: dim_128 |
| | metrics: |
| | - type: cosine_accuracy@1 |
| | value: 0.47 |
| | name: Cosine Accuracy@1 |
| | - type: cosine_accuracy@3 |
| | value: 0.47 |
| | name: Cosine Accuracy@3 |
| | - type: cosine_accuracy@5 |
| | value: 0.47 |
| | name: Cosine Accuracy@5 |
| | - type: cosine_accuracy@10 |
| | value: 0.58 |
| | name: Cosine Accuracy@10 |
| | - type: cosine_precision@1 |
| | value: 0.47 |
| | name: Cosine Precision@1 |
| | - type: cosine_precision@3 |
| | value: 0.47 |
| | name: Cosine Precision@3 |
| | - type: cosine_precision@5 |
| | value: 0.47 |
| | name: Cosine Precision@5 |
| | - type: cosine_precision@10 |
| | value: 0.29 |
| | name: Cosine Precision@10 |
| | - type: cosine_recall@1 |
| | value: 0.09399999999999999 |
| | name: Cosine Recall@1 |
| | - type: cosine_recall@3 |
| | value: 0.28200000000000003 |
| | name: Cosine Recall@3 |
| | - type: cosine_recall@5 |
| | value: 0.47 |
| | name: Cosine Recall@5 |
| | - type: cosine_recall@10 |
| | value: 0.58 |
| | name: Cosine Recall@10 |
| | - type: cosine_ndcg@10 |
| | value: 0.5295093969556788 |
| | name: Cosine Ndcg@10 |
| | - type: cosine_mrr@10 |
| | value: 0.48833333333333323 |
| | name: Cosine Mrr@10 |
| | - type: cosine_map@100 |
| | value: 0.5581789904714569 |
| | name: Cosine Map@100 |
| | - task: |
| | type: information-retrieval |
| | name: Information Retrieval |
| | dataset: |
| | name: dim 64 |
| | type: dim_64 |
| | metrics: |
| | - type: cosine_accuracy@1 |
| | value: 0.5 |
| | name: Cosine Accuracy@1 |
| | - type: cosine_accuracy@3 |
| | value: 0.5 |
| | name: Cosine Accuracy@3 |
| | - type: cosine_accuracy@5 |
| | value: 0.5 |
| | name: Cosine Accuracy@5 |
| | - type: cosine_accuracy@10 |
| | value: 0.6 |
| | name: Cosine Accuracy@10 |
| | - type: cosine_precision@1 |
| | value: 0.5 |
| | name: Cosine Precision@1 |
| | - type: cosine_precision@3 |
| | value: 0.5 |
| | name: Cosine Precision@3 |
| | - type: cosine_precision@5 |
| | value: 0.5 |
| | name: Cosine Precision@5 |
| | - type: cosine_precision@10 |
| | value: 0.3 |
| | name: Cosine Precision@10 |
| | - type: cosine_recall@1 |
| | value: 0.1 |
| | name: Cosine Recall@1 |
| | - type: cosine_recall@3 |
| | value: 0.3 |
| | name: Cosine Recall@3 |
| | - type: cosine_recall@5 |
| | value: 0.5 |
| | name: Cosine Recall@5 |
| | - type: cosine_recall@10 |
| | value: 0.6 |
| | name: Cosine Recall@10 |
| | - type: cosine_ndcg@10 |
| | value: 0.5540994517778899 |
| | name: Cosine Ndcg@10 |
| | - type: cosine_mrr@10 |
| | value: 0.5166666666666665 |
| | name: Cosine Mrr@10 |
| | - type: cosine_map@100 |
| | value: 0.5748485156077728 |
| | name: Cosine Map@100 |
| | --- |
| | |
| | # CodeBERT Fine-tuned on CrewAI |
| |
|
| | This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. |
| |
|
| | ## Model Details |
| |
|
| | ### Model Description |
| | - **Model Type:** Sentence Transformer |
| | - **Base model:** [microsoft/codebert-base](https://huggingface.co/microsoft/codebert-base) <!-- at revision 3b0952feddeffad0063f274080e3c23d75e7eb39 --> |
| | - **Maximum Sequence Length:** 512 tokens |
| | - **Output Dimensionality:** 768 dimensions |
| | - **Similarity Function:** Cosine Similarity |
| | <!-- - **Training Dataset:** Unknown --> |
| | - **Language:** en |
| | - **License:** apache-2.0 |
| |
|
| | ### Model Sources |
| |
|
| | - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
| | - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers) |
| | - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) |
| |
|
| | ### Full Model Architecture |
| |
|
| | ``` |
| | SentenceTransformer( |
| | (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'RobertaModel'}) |
| | (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) |
| | ) |
| | ``` |
| |
|
| | ## Usage |
| |
|
| | ### Direct Usage (Sentence Transformers) |
| |
|
| | First install the Sentence Transformers library: |
| |
|
| | ```bash |
| | pip install -U sentence-transformers |
| | ``` |
| |
|
| | Then you can load this model and run inference. |
| | ```python |
| | from sentence_transformers import SentenceTransformer |
| | |
| | # Download from the 🤗 Hub |
| | model = SentenceTransformer("itsanan/codebert-embed-crewai-base") |
| | # Run inference |
| | sentences = [ |
| | 'Best practices for handle_a2a_polling_started', |
| | 'def handle_a2a_polling_started(\n self,\n task_id: str,\n polling_interval: float,\n endpoint: str,\n ) -> None:\n """Handle A2A polling started event with panel display."""\n content = Text()\n content.append("A2A Polling Started\\n", style="cyan bold")\n content.append("Task ID: ", style="white")\n content.append(f"{task_id[:8]}...\\n", style="cyan")\n content.append("Interval: ", style="white")\n content.append(f"{polling_interval}s\\n", style="cyan")\n\n self.print_panel(content, "⏳ A2A Polling", "cyan")', |
| | 'def test_agent_with_knowledge_sources_generate_search_query():\n content = "Brandon\'s favorite color is red and he likes Mexican food."\n string_source = StringKnowledgeSource(content=content)\n\n with (\n patch("crewai.knowledge") as mock_knowledge,\n patch(\n "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"\n ) as mock_knowledge_storage,\n patch(\n "crewai.knowledge.source.base_knowledge_source.KnowledgeStorage"\n ) as mock_base_knowledge_storage,\n patch("crewai.rag.chromadb.client.ChromaDBClient") as mock_chromadb,\n ):\n mock_knowledge_instance = mock_knowledge.return_value\n mock_knowledge_instance.sources = [string_source]\n mock_knowledge_instance.query.return_value = [{"content": content}]\n\n mock_storage_instance = mock_knowledge_storage.return_value\n mock_storage_instance.sources = [string_source]\n mock_storage_instance.query.return_value = [{"content": content}]\n mock_storage_instance.save.return_value = None\n\n mock_chromadb_instance = mock_chromadb.return_value\n mock_chromadb_instance.add_documents.return_value = None\n\n mock_base_knowledge_storage.return_value = mock_storage_instance\n\n agent = Agent(\n role="Information Agent with extensive role description that is longer than 80 characters",\n goal="Provide information based on knowledge sources",\n backstory="You have access to specific knowledge sources.",\n llm=LLM(model="gpt-4o-mini"),\n knowledge_sources=[string_source],\n )\n\n task = Task(\n description="What is Brandon\'s favorite color?",\n expected_output="The answer to the question, in a format like this: `{{name: str, favorite_color: str}}`",\n agent=agent,\n )\n\n crew = Crew(agents=[agent], tasks=[task])\n result = crew.kickoff()\n\n # Updated assertion to check the JSON content\n assert "Brandon" in str(agent.knowledge_search_query)\n assert "favorite color" in str(agent.knowledge_search_query)\n\n assert "red" in result.raw.lower()', |
| | ] |
| | embeddings = model.encode(sentences) |
| | print(embeddings.shape) |
| | # [3, 768] |
| | |
| | # Get the similarity scores for the embeddings |
| | similarities = model.similarity(embeddings, embeddings) |
| | print(similarities) |
| | # tensor([[1.0000, 0.7350, 0.6480], |
| | # [0.7350, 1.0000, 0.8133], |
| | # [0.6480, 0.8133, 1.0000]]) |
| | ``` |
| |
|
| | <!-- |
| | ### Direct Usage (Transformers) |
| |
|
| | <details><summary>Click to see the direct usage in Transformers</summary> |
| |
|
| | </details> |
| | --> |
| |
|
| | <!-- |
| | ### Downstream Usage (Sentence Transformers) |
| |
|
| | You can finetune this model on your own dataset. |
| |
|
| | <details><summary>Click to expand</summary> |
| |
|
| | </details> |
| | --> |
| |
|
| | <!-- |
| | ### Out-of-Scope Use |
| |
|
| | *List how the model may foreseeably be misused and address what users ought not to do with the model.* |
| | --> |
| |
|
| | ## Evaluation |
| |
|
| | ### Metrics |
| |
|
| | #### Information Retrieval |
| |
|
| | * Dataset: `dim_768` |
| | * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: |
| | ```json |
| | { |
| | "truncate_dim": 768 |
| | } |
| | ``` |
| |
|
| | | Metric | Value | |
| | |:--------------------|:-----------| |
| | | cosine_accuracy@1 | 0.57 | |
| | | cosine_accuracy@3 | 0.57 | |
| | | cosine_accuracy@5 | 0.57 | |
| | | cosine_accuracy@10 | 0.65 | |
| | | cosine_precision@1 | 0.57 | |
| | | cosine_precision@3 | 0.57 | |
| | | cosine_precision@5 | 0.57 | |
| | | cosine_precision@10 | 0.325 | |
| | | cosine_recall@1 | 0.114 | |
| | | cosine_recall@3 | 0.342 | |
| | | cosine_recall@5 | 0.57 | |
| | | cosine_recall@10 | 0.65 | |
| | | **cosine_ndcg@10** | **0.6133** | |
| | | cosine_mrr@10 | 0.5833 | |
| | | cosine_map@100 | 0.6323 | |
| | |
| | #### Information Retrieval |
| | |
| | * Dataset: `dim_512` |
| | * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: |
| | ```json |
| | { |
| | "truncate_dim": 512 |
| | } |
| | ``` |
| | |
| | | Metric | Value | |
| | |:--------------------|:-----------| |
| | | cosine_accuracy@1 | 0.56 | |
| | | cosine_accuracy@3 | 0.56 | |
| | | cosine_accuracy@5 | 0.56 | |
| | | cosine_accuracy@10 | 0.68 | |
| | | cosine_precision@1 | 0.56 | |
| | | cosine_precision@3 | 0.56 | |
| | | cosine_precision@5 | 0.56 | |
| | | cosine_precision@10 | 0.34 | |
| | | cosine_recall@1 | 0.112 | |
| | | cosine_recall@3 | 0.336 | |
| | | cosine_recall@5 | 0.56 | |
| | | cosine_recall@10 | 0.68 | |
| | | **cosine_ndcg@10** | **0.6249** | |
| | | cosine_mrr@10 | 0.58 | |
| | | cosine_map@100 | 0.6328 | |
| |
|
| | #### Information Retrieval |
| |
|
| | * Dataset: `dim_256` |
| | * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: |
| | ```json |
| | { |
| | "truncate_dim": 256 |
| | } |
| | ``` |
| |
|
| | | Metric | Value | |
| | |:--------------------|:-----------| |
| | | cosine_accuracy@1 | 0.54 | |
| | | cosine_accuracy@3 | 0.54 | |
| | | cosine_accuracy@5 | 0.54 | |
| | | cosine_accuracy@10 | 0.67 | |
| | | cosine_precision@1 | 0.54 | |
| | | cosine_precision@3 | 0.54 | |
| | | cosine_precision@5 | 0.54 | |
| | | cosine_precision@10 | 0.335 | |
| | | cosine_recall@1 | 0.108 | |
| | | cosine_recall@3 | 0.324 | |
| | | cosine_recall@5 | 0.54 | |
| | | cosine_recall@10 | 0.67 | |
| | | **cosine_ndcg@10** | **0.6103** | |
| | | cosine_mrr@10 | 0.5617 | |
| | | cosine_map@100 | 0.6227 | |
| | |
| | #### Information Retrieval |
| | |
| | * Dataset: `dim_128` |
| | * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: |
| | ```json |
| | { |
| | "truncate_dim": 128 |
| | } |
| | ``` |
| | |
| | | Metric | Value | |
| | |:--------------------|:-----------| |
| | | cosine_accuracy@1 | 0.47 | |
| | | cosine_accuracy@3 | 0.47 | |
| | | cosine_accuracy@5 | 0.47 | |
| | | cosine_accuracy@10 | 0.58 | |
| | | cosine_precision@1 | 0.47 | |
| | | cosine_precision@3 | 0.47 | |
| | | cosine_precision@5 | 0.47 | |
| | | cosine_precision@10 | 0.29 | |
| | | cosine_recall@1 | 0.094 | |
| | | cosine_recall@3 | 0.282 | |
| | | cosine_recall@5 | 0.47 | |
| | | cosine_recall@10 | 0.58 | |
| | | **cosine_ndcg@10** | **0.5295** | |
| | | cosine_mrr@10 | 0.4883 | |
| | | cosine_map@100 | 0.5582 | |
| |
|
| | #### Information Retrieval |
| |
|
| | * Dataset: `dim_64` |
| | * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters: |
| | ```json |
| | { |
| | "truncate_dim": 64 |
| | } |
| | ``` |
| |
|
| | | Metric | Value | |
| | |:--------------------|:-----------| |
| | | cosine_accuracy@1 | 0.5 | |
| | | cosine_accuracy@3 | 0.5 | |
| | | cosine_accuracy@5 | 0.5 | |
| | | cosine_accuracy@10 | 0.6 | |
| | | cosine_precision@1 | 0.5 | |
| | | cosine_precision@3 | 0.5 | |
| | | cosine_precision@5 | 0.5 | |
| | | cosine_precision@10 | 0.3 | |
| | | cosine_recall@1 | 0.1 | |
| | | cosine_recall@3 | 0.3 | |
| | | cosine_recall@5 | 0.5 | |
| | | cosine_recall@10 | 0.6 | |
| | | **cosine_ndcg@10** | **0.5541** | |
| | | cosine_mrr@10 | 0.5167 | |
| | | cosine_map@100 | 0.5748 | |
| | |
| | <!-- |
| | ## Bias, Risks and Limitations |
| | |
| | *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
| | --> |
| | |
| | <!-- |
| | ### Recommendations |
| | |
| | *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
| | --> |
| | |
| | ## Training Details |
| | |
| | ### Training Dataset |
| | |
| | #### Unnamed Dataset |
| | |
| | * Size: 900 training samples |
| | * Columns: <code>anchor</code> and <code>positive</code> |
| | * Approximate statistics based on the first 900 samples: |
| | | | anchor | positive | |
| | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| |
| | | type | string | string | |
| | | details | <ul><li>min: 6 tokens</li><li>mean: 13.96 tokens</li><li>max: 141 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 254.94 tokens</li><li>max: 512 tokens</li></ul> | |
| | * Samples: |
| | | anchor | positive | |
| | |:---------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| | | <code>Example usage of DeeplyNestedFlow</code> | <code>class DeeplyNestedFlow(Flow):<br> @start()<br> def a(self):<br> execution_order.append("a")<br><br> @start()<br> def b(self):<br> execution_order.append("b")<br><br> @start()<br> def c(self):<br> execution_order.append("c")<br><br> @start()<br> def d(self):<br> execution_order.append("d")<br><br> # Nested: (a AND b) OR (c AND d)<br> @listen(or_(and_(a, b), and_(c, d)))<br> def result(self):<br> execution_order.append("result")</code> | |
| | | <code>Explain the test_agent_with_knowledge_sources_generate_search_query logic</code> | <code>def test_agent_with_knowledge_sources_generate_search_query():<br> content = "Brandon's favorite color is red and he likes Mexican food."<br> string_source = StringKnowledgeSource(content=content)<br><br> with (<br> patch("crewai.knowledge") as mock_knowledge,<br> patch(<br> "crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"<br> ) as mock_knowledge_storage,<br> patch(<br> "crewai.knowledge.source.base_knowledge_source.KnowledgeStorage"<br> ) as mock_base_knowledge_storage,<br> patch("crewai.rag.chromadb.client.ChromaDBClient") as mock_chromadb,<br> ):<br> mock_knowledge_instance = mock_knowledge.return_value<br> mock_knowledge_instance.sources = [string_source]<br> mock_knowledge_instance.query.return_value = [{"content": content}]<br><br> mock_storage_instance = mock_knowledge_storage.return_value<br> mock_storage_instance.sources = [string_source]<br> mock_storage_instance.query.return_value = [{"content": content}]...</code> | |
| | | <code>Example usage of agent</code> | <code>def agent(self) -> Agent \| None:<br> """Get the current agent associated with this memory."""<br> return self._agent</code> | |
| | * Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters: |
| | ```json |
| | { |
| | "loss": "MultipleNegativesRankingLoss", |
| | "matryoshka_dims": [ |
| | 768, |
| | 512, |
| | 256, |
| | 128, |
| | 64 |
| | ], |
| | "matryoshka_weights": [ |
| | 1, |
| | 1, |
| | 1, |
| | 1, |
| | 1 |
| | ], |
| | "n_dims_per_step": -1 |
| | } |
| | ``` |
| | |
| | ### Training Hyperparameters |
| | #### Non-Default Hyperparameters |
| | |
| | - `eval_strategy`: epoch |
| | - `per_device_train_batch_size`: 4 |
| | - `per_device_eval_batch_size`: 4 |
| | - `gradient_accumulation_steps`: 16 |
| | - `learning_rate`: 2e-05 |
| | - `num_train_epochs`: 4 |
| | - `lr_scheduler_type`: cosine |
| | - `warmup_ratio`: 0.1 |
| | - `fp16`: True |
| | - `load_best_model_at_end`: True |
| | - `optim`: adamw_torch |
| | - `batch_sampler`: no_duplicates |
| | |
| | #### All Hyperparameters |
| | <details><summary>Click to expand</summary> |
| | |
| | - `overwrite_output_dir`: False |
| | - `do_predict`: False |
| | - `eval_strategy`: epoch |
| | - `prediction_loss_only`: True |
| | - `per_device_train_batch_size`: 4 |
| | - `per_device_eval_batch_size`: 4 |
| | - `per_gpu_train_batch_size`: None |
| | - `per_gpu_eval_batch_size`: None |
| | - `gradient_accumulation_steps`: 16 |
| | - `eval_accumulation_steps`: None |
| | - `torch_empty_cache_steps`: None |
| | - `learning_rate`: 2e-05 |
| | - `weight_decay`: 0.0 |
| | - `adam_beta1`: 0.9 |
| | - `adam_beta2`: 0.999 |
| | - `adam_epsilon`: 1e-08 |
| | - `max_grad_norm`: 1.0 |
| | - `num_train_epochs`: 4 |
| | - `max_steps`: -1 |
| | - `lr_scheduler_type`: cosine |
| | - `lr_scheduler_kwargs`: None |
| | - `warmup_ratio`: 0.1 |
| | - `warmup_steps`: 0 |
| | - `log_level`: passive |
| | - `log_level_replica`: warning |
| | - `log_on_each_node`: True |
| | - `logging_nan_inf_filter`: True |
| | - `save_safetensors`: True |
| | - `save_on_each_node`: False |
| | - `save_only_model`: False |
| | - `restore_callback_states_from_checkpoint`: False |
| | - `no_cuda`: False |
| | - `use_cpu`: False |
| | - `use_mps_device`: False |
| | - `seed`: 42 |
| | - `data_seed`: None |
| | - `jit_mode_eval`: False |
| | - `bf16`: False |
| | - `fp16`: True |
| | - `fp16_opt_level`: O1 |
| | - `half_precision_backend`: auto |
| | - `bf16_full_eval`: False |
| | - `fp16_full_eval`: False |
| | - `tf32`: None |
| | - `local_rank`: 0 |
| | - `ddp_backend`: None |
| | - `tpu_num_cores`: None |
| | - `tpu_metrics_debug`: False |
| | - `debug`: [] |
| | - `dataloader_drop_last`: False |
| | - `dataloader_num_workers`: 0 |
| | - `dataloader_prefetch_factor`: None |
| | - `past_index`: -1 |
| | - `disable_tqdm`: False |
| | - `remove_unused_columns`: True |
| | - `label_names`: None |
| | - `load_best_model_at_end`: True |
| | - `ignore_data_skip`: False |
| | - `fsdp`: [] |
| | - `fsdp_min_num_params`: 0 |
| | - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
| | - `fsdp_transformer_layer_cls_to_wrap`: None |
| | - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
| | - `parallelism_config`: None |
| | - `deepspeed`: None |
| | - `label_smoothing_factor`: 0.0 |
| | - `optim`: adamw_torch |
| | - `optim_args`: None |
| | - `adafactor`: False |
| | - `group_by_length`: False |
| | - `length_column_name`: length |
| | - `project`: huggingface |
| | - `trackio_space_id`: trackio |
| | - `ddp_find_unused_parameters`: None |
| | - `ddp_bucket_cap_mb`: None |
| | - `ddp_broadcast_buffers`: False |
| | - `dataloader_pin_memory`: True |
| | - `dataloader_persistent_workers`: False |
| | - `skip_memory_metrics`: True |
| | - `use_legacy_prediction_loop`: False |
| | - `push_to_hub`: False |
| | - `resume_from_checkpoint`: None |
| | - `hub_model_id`: None |
| | - `hub_strategy`: every_save |
| | - `hub_private_repo`: None |
| | - `hub_always_push`: False |
| | - `hub_revision`: None |
| | - `gradient_checkpointing`: False |
| | - `gradient_checkpointing_kwargs`: None |
| | - `include_inputs_for_metrics`: False |
| | - `include_for_metrics`: [] |
| | - `eval_do_concat_batches`: True |
| | - `fp16_backend`: auto |
| | - `push_to_hub_model_id`: None |
| | - `push_to_hub_organization`: None |
| | - `mp_parameters`: |
| | - `auto_find_batch_size`: False |
| | - `full_determinism`: False |
| | - `torchdynamo`: None |
| | - `ray_scope`: last |
| | - `ddp_timeout`: 1800 |
| | - `torch_compile`: False |
| | - `torch_compile_backend`: None |
| | - `torch_compile_mode`: None |
| | - `include_tokens_per_second`: False |
| | - `include_num_input_tokens_seen`: no |
| | - `neftune_noise_alpha`: None |
| | - `optim_target_modules`: None |
| | - `batch_eval_metrics`: False |
| | - `eval_on_start`: False |
| | - `use_liger_kernel`: False |
| | - `liger_kernel_config`: None |
| | - `eval_use_gather_object`: False |
| | - `average_tokens_across_devices`: True |
| | - `prompts`: None |
| | - `batch_sampler`: no_duplicates |
| | - `multi_dataset_batch_sampler`: proportional |
| | - `router_mapping`: {} |
| | - `learning_rate_mapping`: {} |
| | |
| | </details> |
| | |
| | ### Training Logs |
| | | Epoch | Step | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 | |
| | |:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:| |
| | | 0.7111 | 10 | 7.1051 | - | - | - | - | - | |
| | | 1.0 | 15 | - | 0.1170 | 0.06 | 0.0608 | 0.0825 | 0.0762 | |
| | | 1.3556 | 20 | 6.4716 | - | - | - | - | - | |
| | | 2.0 | 30 | 5.4463 | 0.1879 | 0.1770 | 0.1625 | 0.1816 | 0.1987 | |
| | | 2.7111 | 40 | 3.7856 | - | - | - | - | - | |
| | | 3.0 | 45 | - | 0.4987 | 0.5133 | 0.4587 | 0.4249 | 0.4425 | |
| | | 3.3556 | 50 | 2.4942 | - | - | - | - | - | |
| | | **4.0** | **60** | **1.71** | **0.6133** | **0.6249** | **0.6103** | **0.5295** | **0.5541** | |
| |
|
| | * The bold row denotes the saved checkpoint. |
| |
|
| | ### Framework Versions |
| | - Python: 3.12.12 |
| | - Sentence Transformers: 5.2.2 |
| | - Transformers: 4.57.6 |
| | - PyTorch: 2.9.0+cu126 |
| | - Accelerate: 1.12.0 |
| | - Datasets: 4.0.0 |
| | - Tokenizers: 0.22.2 |
| |
|
| | ## Citation |
| |
|
| | ### BibTeX |
| |
|
| | #### Sentence Transformers |
| | ```bibtex |
| | @inproceedings{reimers-2019-sentence-bert, |
| | title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
| | author = "Reimers, Nils and Gurevych, Iryna", |
| | booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
| | month = "11", |
| | year = "2019", |
| | publisher = "Association for Computational Linguistics", |
| | url = "https://arxiv.org/abs/1908.10084", |
| | } |
| | ``` |
| |
|
| | #### MatryoshkaLoss |
| | ```bibtex |
| | @misc{kusupati2024matryoshka, |
| | title={Matryoshka Representation Learning}, |
| | author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi}, |
| | year={2024}, |
| | eprint={2205.13147}, |
| | archivePrefix={arXiv}, |
| | primaryClass={cs.LG} |
| | } |
| | ``` |
| |
|
| | #### MultipleNegativesRankingLoss |
| | ```bibtex |
| | @misc{henderson2017efficient, |
| | title={Efficient Natural Language Response Suggestion for Smart Reply}, |
| | author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, |
| | year={2017}, |
| | eprint={1705.00652}, |
| | archivePrefix={arXiv}, |
| | primaryClass={cs.CL} |
| | } |
| | ``` |
| |
|
| | <!-- |
| | ## Glossary |
| |
|
| | *Clearly define terms in order to be accessible across audiences.* |
| | --> |
| |
|
| | <!-- |
| | ## Model Card Authors |
| |
|
| | *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
| | --> |
| |
|
| | <!-- |
| | ## Model Card Contact |
| |
|
| | *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
| | --> |
