---
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.*
-->