diff --git a/docs/en/observability/datadog.mdx b/docs/en/observability/datadog.mdx
index b2c72733a..0094446c5 100644
--- a/docs/en/observability/datadog.mdx
+++ b/docs/en/observability/datadog.mdx
@@ -93,11 +93,15 @@ After running the application, you can view the traces in [Datadog LLM Observabi
Clicking on a trace will show you the details of the trace, including total tokens used, number of LLM calls, models used, and estimated cost. Clicking into a specific span will narrow down these details, and show related input, output, and metadata.
-
+
+
+
Additionally, you can view the execution graph view of the trace, which shows the control and data flow of the trace, which will scale with larger agents to show handoffs and relationships between LLM calls, tool calls, and agent interactions.
-
+
+
+
## References
diff --git a/docs/en/tools/file-document/csvsearchtool.mdx b/docs/en/tools/file-document/csvsearchtool.mdx
index 58d519332..c20f8ec74 100644
--- a/docs/en/tools/file-document/csvsearchtool.mdx
+++ b/docs/en/tools/file-document/csvsearchtool.mdx
@@ -54,25 +54,25 @@ The following parameters can be used to customize the `CSVSearchTool`'s behavior
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
+from chromadb.config import Settings
+
tool = CSVSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/en/tools/file-document/directorysearchtool.mdx b/docs/en/tools/file-document/directorysearchtool.mdx
index 4ba111636..9efd2e910 100644
--- a/docs/en/tools/file-document/directorysearchtool.mdx
+++ b/docs/en/tools/file-document/directorysearchtool.mdx
@@ -46,23 +46,25 @@ tool = DirectorySearchTool(directory='/path/to/directory')
The DirectorySearchTool uses OpenAI for embeddings and summarization by default. Customization options for these settings include changing the model provider and configuration, enhancing flexibility for advanced users.
```python Code
+from chromadb.config import Settings
+
tool = DirectorySearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # Options include ollama, google, anthropic, llama2, and more
- config=dict(
- model="llama2",
- # Additional configurations here
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/en/tools/file-document/docxsearchtool.mdx b/docs/en/tools/file-document/docxsearchtool.mdx
index c70dc7ab4..6e9c85719 100644
--- a/docs/en/tools/file-document/docxsearchtool.mdx
+++ b/docs/en/tools/file-document/docxsearchtool.mdx
@@ -56,25 +56,25 @@ The following parameters can be used to customize the `DOCXSearchTool`'s behavio
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
+from chromadb.config import Settings
+
tool = DOCXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/en/tools/file-document/mdxsearchtool.mdx b/docs/en/tools/file-document/mdxsearchtool.mdx
index c6b0ec2bc..83c64a06b 100644
--- a/docs/en/tools/file-document/mdxsearchtool.mdx
+++ b/docs/en/tools/file-document/mdxsearchtool.mdx
@@ -48,27 +48,25 @@ tool = MDXSearchTool(mdx='path/to/your/document.mdx')
The tool defaults to using OpenAI for embeddings and summarization. For customization, utilize a configuration dictionary as shown below:
```python Code
+from chromadb.config import Settings
+
tool = MDXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # Options include google, openai, anthropic, llama2, etc.
- config=dict(
- model="llama2",
- # Optional parameters can be included here.
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # Optional title for the embeddings can be added here.
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/en/tools/file-document/pdfsearchtool.mdx b/docs/en/tools/file-document/pdfsearchtool.mdx
index 68d15a55d..cede7cfe2 100644
--- a/docs/en/tools/file-document/pdfsearchtool.mdx
+++ b/docs/en/tools/file-document/pdfsearchtool.mdx
@@ -45,28 +45,64 @@ tool = PDFSearchTool(pdf='path/to/your/document.pdf')
## Custom model and embeddings
-By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
+By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows. Note: a vector database is required because generated embeddings must be stored and queried from a vectordb.
```python Code
+from crewai_tools import PDFSearchTool
+
+# - embedding_model (required): choose provider + provider-specific config
+# - vectordb (required): choose vector DB and pass its config
+
tool = PDFSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ # Supported providers: "openai", "azure", "google-generativeai", "google-vertex",
+ # "voyageai", "cohere", "huggingface", "jina", "sentence-transformer",
+ # "text2vec", "ollama", "openclip", "instructor", "onnx", "roboflow", "watsonx", "custom"
+ "provider": "openai", # or: "google-generativeai", "cohere", "ollama", ...
+ "config": {
+ # Model identifier for the chosen provider. "model" will be auto-mapped to "model_name" internally.
+ "model": "text-embedding-3-small",
+ # Optional: API key. If omitted, the tool will use provider-specific env vars when available
+ # (e.g., OPENAI_API_KEY for provider="openai").
+ # "api_key": "sk-...",
+
+ # Provider-specific examples:
+ # --- Google Generative AI ---
+ # (Set provider="google-generativeai" above)
+ # "model": "models/embedding-001",
+ # "task_type": "retrieval_document",
+ # "title": "Embeddings",
+
+ # --- Cohere ---
+ # (Set provider="cohere" above)
+ # "model": "embed-english-v3.0",
+
+ # --- Ollama (local) ---
+ # (Set provider="ollama" above)
+ # "model": "nomic-embed-text",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # For ChromaDB: pass "settings" (chromadb.config.Settings) or rely on defaults.
+ # Example (uncomment and import):
+ # from chromadb.config import Settings
+ # "settings": Settings(
+ # persist_directory="/content/chroma",
+ # allow_reset=True,
+ # is_persistent=True,
+ # ),
+
+ # For Qdrant: pass "vectors_config" (qdrant_client.models.VectorParams).
+ # Example (uncomment and import):
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # Note: collection name is controlled by the tool (default: "rag_tool_collection"), not set here.
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/en/tools/file-document/txtsearchtool.mdx b/docs/en/tools/file-document/txtsearchtool.mdx
index 7683d9954..4c4b0d91d 100644
--- a/docs/en/tools/file-document/txtsearchtool.mdx
+++ b/docs/en/tools/file-document/txtsearchtool.mdx
@@ -57,25 +57,41 @@ By default, the tool uses OpenAI for both embeddings and summarization.
To customize the model, you can use a config dictionary as follows:
```python Code
+from chromadb.config import Settings
+
tool = TXTSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ # Required: embeddings provider + config
+ "embedding_model": {
+ "provider": "openai", # or google-generativeai, cohere, ollama, ...
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...", # optional if env var is set
+ # Provider examples:
+ # Google → model: "models/embedding-001", task_type: "retrieval_document"
+ # Cohere → model: "embed-english-v3.0"
+ # Ollama → model: "nomic-embed-text"
+ },
+ },
+
+ # Required: vector database config
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # Chroma settings (optional persistence)
+ # "settings": Settings(
+ # persist_directory="/content/chroma",
+ # allow_reset=True,
+ # is_persistent=True,
+ # ),
+
+ # Qdrant vector params example:
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # Note: collection name is controlled by the tool (default: "rag_tool_collection").
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/en/tools/file-document/xmlsearchtool.mdx b/docs/en/tools/file-document/xmlsearchtool.mdx
index d0ba026b6..5f57b7837 100644
--- a/docs/en/tools/file-document/xmlsearchtool.mdx
+++ b/docs/en/tools/file-document/xmlsearchtool.mdx
@@ -54,25 +54,25 @@ It is an optional parameter during the tool's initialization but must be provide
By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
```python Code
+from chromadb.config import Settings
+
tool = XMLSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # or "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/ko/observability/datadog.mdx b/docs/ko/observability/datadog.mdx
index 5e28c6334..38bc778ce 100644
--- a/docs/ko/observability/datadog.mdx
+++ b/docs/ko/observability/datadog.mdx
@@ -93,11 +93,15 @@ ddtrace-run python crewai_agent.py
트레이스를 클릭하면 사용된 총 토큰, LLM 호출 수, 사용된 모델, 예상 비용 등 트레이스에 대한 세부 정보가 표시됩니다. 특정 스팬(span)을 클릭하면 이러한 세부 정보의 범위가 좁혀지고 관련 입력, 출력 및 메타데이터가 표시됩니다.
-
+
+
+
또한, 트레이스의 제어 및 데이터 흐름을 보여주는 트레이스의 실행 그래프 보기를 볼 수 있으며, 이는 더 큰 에이전트로 확장하여 LLM 호출, 도구 호출 및 에이전트 상호 작용 간의 핸드오프와 관계를 보여줍니다.
-
+
+
+
## 참조
diff --git a/docs/ko/tools/file-document/csvsearchtool.mdx b/docs/ko/tools/file-document/csvsearchtool.mdx
index 0dd8f7bad..e962b11e1 100644
--- a/docs/ko/tools/file-document/csvsearchtool.mdx
+++ b/docs/ko/tools/file-document/csvsearchtool.mdx
@@ -54,25 +54,25 @@ tool = CSVSearchTool()
기본적으로 이 도구는 임베딩과 요약 모두에 OpenAI를 사용합니다. 모델을 사용자 지정하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다:
```python Code
+from chromadb.config import Settings
+
tool = CSVSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/directorysearchtool.mdx b/docs/ko/tools/file-document/directorysearchtool.mdx
index 5b8979b4c..5a46e53b7 100644
--- a/docs/ko/tools/file-document/directorysearchtool.mdx
+++ b/docs/ko/tools/file-document/directorysearchtool.mdx
@@ -46,23 +46,25 @@ tool = DirectorySearchTool(directory='/path/to/directory')
DirectorySearchTool은 기본적으로 OpenAI를 사용하여 임베딩 및 요약을 수행합니다. 이 설정의 커스터마이즈 옵션에는 모델 공급자 및 구성을 변경하는 것이 포함되어 있어, 고급 사용자를 위한 유연성을 향상시킵니다.
```python Code
+from chromadb.config import Settings
+
tool = DirectorySearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # Options include ollama, google, anthropic, llama2, and more
- config=dict(
- model="llama2",
- # Additional configurations here
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/docxsearchtool.mdx b/docs/ko/tools/file-document/docxsearchtool.mdx
index c20b1dcf7..81c74a7b2 100644
--- a/docs/ko/tools/file-document/docxsearchtool.mdx
+++ b/docs/ko/tools/file-document/docxsearchtool.mdx
@@ -56,25 +56,25 @@ tool = DOCXSearchTool(docx='path/to/your/document.docx')
기본적으로 이 도구는 임베딩과 요약 모두에 OpenAI를 사용합니다. 모델을 커스터마이즈하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다:
```python Code
+from chromadb.config import Settings
+
tool = DOCXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/mdxsearchtool.mdx b/docs/ko/tools/file-document/mdxsearchtool.mdx
index bbcf971cb..282d2d8e2 100644
--- a/docs/ko/tools/file-document/mdxsearchtool.mdx
+++ b/docs/ko/tools/file-document/mdxsearchtool.mdx
@@ -48,27 +48,25 @@ tool = MDXSearchTool(mdx='path/to/your/document.mdx')
이 도구는 기본적으로 임베딩과 요약을 위해 OpenAI를 사용합니다. 커스터마이징을 위해 아래와 같이 설정 딕셔너리를 사용할 수 있습니다.
```python Code
+from chromadb.config import Settings
+
tool = MDXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # 옵션에는 google, openai, anthropic, llama2 등이 있습니다.
- config=dict(
- model="llama2",
- # 선택적 파라미터를 여기에 포함할 수 있습니다.
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # 또는 openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # 임베딩에 대한 선택적 제목을 여기에 추가할 수 있습니다.
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/pdfsearchtool.mdx b/docs/ko/tools/file-document/pdfsearchtool.mdx
index c34193a6a..573ed4812 100644
--- a/docs/ko/tools/file-document/pdfsearchtool.mdx
+++ b/docs/ko/tools/file-document/pdfsearchtool.mdx
@@ -45,28 +45,60 @@ tool = PDFSearchTool(pdf='path/to/your/document.pdf')
## 커스텀 모델 및 임베딩
-기본적으로 이 도구는 임베딩과 요약 모두에 OpenAI를 사용합니다. 모델을 커스터마이즈하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다:
+기본적으로 이 도구는 임베딩과 요약 모두에 OpenAI를 사용합니다. 모델을 커스터마이즈하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다. 참고: 임베딩은 벡터DB에 저장되어야 하므로 vectordb 설정이 필요합니다.
```python Code
+from crewai_tools import PDFSearchTool
+from chromadb.config import Settings # Chroma 영속성 설정
+
tool = PDFSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ # 필수: 임베딩 제공자와 설정
+ "embedding_model": {
+ # 사용 가능 공급자: "openai", "azure", "google-generativeai", "google-vertex",
+ # "voyageai", "cohere", "huggingface", "jina", "sentence-transformer",
+ # "text2vec", "ollama", "openclip", "instructor", "onnx", "roboflow", "watsonx", "custom"
+ "provider": "openai",
+ "config": {
+ # "model" 키는 내부적으로 "model_name"으로 매핑됩니다.
+ "model": "text-embedding-3-small",
+ # 선택: API 키 (미설정 시 환경변수 사용)
+ # "api_key": "sk-...",
+
+ # 공급자별 예시
+ # --- Google ---
+ # (provider를 "google-generativeai"로 설정)
+ # "model": "models/embedding-001",
+ # "task_type": "retrieval_document",
+
+ # --- Cohere ---
+ # (provider를 "cohere"로 설정)
+ # "model": "embed-english-v3.0",
+
+ # --- Ollama(로컬) ---
+ # (provider를 "ollama"로 설정)
+ # "model": "nomic-embed-text",
+ },
+ },
+
+ # 필수: 벡터DB 설정
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # Chroma 설정 예시
+ # "settings": Settings(
+ # persist_directory="/content/chroma",
+ # allow_reset=True,
+ # is_persistent=True,
+ # ),
+
+ # Qdrant 설정 예시
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # 참고: 컬렉션 이름은 도구에서 관리합니다(기본값: "rag_tool_collection").
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/txtsearchtool.mdx b/docs/ko/tools/file-document/txtsearchtool.mdx
index adaf2b0a2..8df143683 100644
--- a/docs/ko/tools/file-document/txtsearchtool.mdx
+++ b/docs/ko/tools/file-document/txtsearchtool.mdx
@@ -57,25 +57,34 @@ tool = TXTSearchTool(txt='path/to/text/file.txt')
모델을 커스터마이징하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다:
```python Code
+from chromadb.config import Settings
+
tool = TXTSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ # 필수: 임베딩 제공자 + 설정
+ "embedding_model": {
+ "provider": "openai", # 또는 google-generativeai, cohere, ollama 등
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...", # 환경변수 사용 시 생략 가능
+ # 공급자별 예시: Google → model: "models/embedding-001", task_type: "retrieval_document"
+ },
+ },
+
+ # 필수: 벡터DB 설정
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # Chroma 설정(영속성 예시)
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+
+ # Qdrant 벡터 파라미터 예시:
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # 참고: 컬렉션 이름은 도구에서 관리합니다(기본값: "rag_tool_collection").
+ }
+ },
+ }
)
```
diff --git a/docs/ko/tools/file-document/xmlsearchtool.mdx b/docs/ko/tools/file-document/xmlsearchtool.mdx
index 7418f9f58..dde5ecf52 100644
--- a/docs/ko/tools/file-document/xmlsearchtool.mdx
+++ b/docs/ko/tools/file-document/xmlsearchtool.mdx
@@ -54,25 +54,25 @@ tool = XMLSearchTool(xml='path/to/your/xmlfile.xml')
기본적으로 이 도구는 임베딩과 요약 모두에 OpenAI를 사용합니다. 모델을 커스터마이징하려면 다음과 같이 config 딕셔너리를 사용할 수 있습니다.
```python Code
+from chromadb.config import Settings
+
tool = XMLSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # or google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # or openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # 또는 "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
diff --git a/docs/pt-BR/observability/datadog.mdx b/docs/pt-BR/observability/datadog.mdx
index 01e5e2e39..a357fea83 100644
--- a/docs/pt-BR/observability/datadog.mdx
+++ b/docs/pt-BR/observability/datadog.mdx
@@ -93,11 +93,14 @@ Depois de executar o aplicativo, você pode visualizar os traços na [Datadog LL
Ao clicar em um rastreamento, você verá os detalhes do rastreamento, incluindo o total de tokens usados, o número de chamadas LLM, os modelos usados e o custo estimado. Clicar em um intervalo específico reduzirá esses detalhes e mostrará a entrada, a saída e os metadados relacionados.
-
-
+
+
+
Além disso, você pode visualizar a visualização do gráfico de execução do rastreamento, que mostra o controle e o fluxo de dados do rastreamento, que será dimensionado com agentes maiores para mostrar transferências e relacionamentos entre chamadas LLM, chamadas de ferramentas e interações de agentes.
-
+
+
+
## Referências
diff --git a/docs/pt-BR/tools/file-document/directorysearchtool.mdx b/docs/pt-BR/tools/file-document/directorysearchtool.mdx
index ea7153a07..4093bbc8e 100644
--- a/docs/pt-BR/tools/file-document/directorysearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/directorysearchtool.mdx
@@ -46,23 +46,25 @@ tool = DirectorySearchTool(directory='/path/to/directory')
O DirectorySearchTool utiliza OpenAI para embeddings e sumarização por padrão. As opções de personalização dessas configurações incluem a alteração do provedor de modelo e configurações, ampliando a flexibilidade para usuários avançados.
```python Code
+from chromadb.config import Settings
+
tool = DirectorySearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # As opções incluem ollama, google, anthropic, llama2 e mais
- config=dict(
- model="llama2",
- # Configurações adicionais aqui
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/pt-BR/tools/file-document/docxsearchtool.mdx b/docs/pt-BR/tools/file-document/docxsearchtool.mdx
index 58d24454c..f9f29115e 100644
--- a/docs/pt-BR/tools/file-document/docxsearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/docxsearchtool.mdx
@@ -56,25 +56,25 @@ Os seguintes parâmetros podem ser usados para customizar o comportamento da `DO
Por padrão, a ferramenta utiliza o OpenAI tanto para embeddings quanto para sumarização. Para customizar o modelo, você pode usar um dicionário de configuração como no exemplo:
```python Code
+from chromadb.config import Settings
+
tool = DOCXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # ou google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/pt-BR/tools/file-document/mdxsearchtool.mdx b/docs/pt-BR/tools/file-document/mdxsearchtool.mdx
index e7cce21e8..93e693e0a 100644
--- a/docs/pt-BR/tools/file-document/mdxsearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/mdxsearchtool.mdx
@@ -48,27 +48,25 @@ tool = MDXSearchTool(mdx='path/to/your/document.mdx')
A ferramenta utiliza, por padrão, o OpenAI para embeddings e sumarização. Para personalizar, utilize um dicionário de configuração conforme exemplo abaixo:
```python Code
+from chromadb.config import Settings
+
tool = MDXSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # As opções incluem google, openai, anthropic, llama2, etc.
- config=dict(
- model="llama2",
- # Parâmetros opcionais podem ser incluídos aqui.
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # Um título opcional para os embeddings pode ser adicionado aqui.
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/pt-BR/tools/file-document/pdfsearchtool.mdx b/docs/pt-BR/tools/file-document/pdfsearchtool.mdx
index 1547e7ef3..83cac48bb 100644
--- a/docs/pt-BR/tools/file-document/pdfsearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/pdfsearchtool.mdx
@@ -45,28 +45,60 @@ tool = PDFSearchTool(pdf='path/to/your/document.pdf')
## Modelo e embeddings personalizados
-Por padrão, a ferramenta utiliza OpenAI tanto para embeddings quanto para sumarização. Para personalizar o modelo, você pode usar um dicionário de configuração como no exemplo abaixo:
+Por padrão, a ferramenta utiliza OpenAI para embeddings e sumarização. Para personalizar, use um dicionário de configuração conforme abaixo. Observação: um banco vetorial (vectordb) é necessário, pois os embeddings gerados precisam ser armazenados e consultados.
```python Code
+from crewai_tools import PDFSearchTool
+from chromadb.config import Settings # Persistência no Chroma
+
tool = PDFSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # ou google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ # Obrigatório: provedor de embeddings + configuração
+ "embedding_model": {
+ # Provedores suportados: "openai", "azure", "google-generativeai", "google-vertex",
+ # "voyageai", "cohere", "huggingface", "jina", "sentence-transformer",
+ # "text2vec", "ollama", "openclip", "instructor", "onnx", "roboflow", "watsonx", "custom"
+ "provider": "openai",
+ "config": {
+ # "model" é mapeado internamente para "model_name".
+ "model": "text-embedding-3-small",
+ # Opcional: chave da API (se ausente, usa variáveis de ambiente do provedor)
+ # "api_key": "sk-...",
+
+ # Exemplos específicos por provedor
+ # --- Google ---
+ # (defina provider="google-generativeai")
+ # "model": "models/embedding-001",
+ # "task_type": "retrieval_document",
+
+ # --- Cohere ---
+ # (defina provider="cohere")
+ # "model": "embed-english-v3.0",
+
+ # --- Ollama (local) ---
+ # (defina provider="ollama")
+ # "model": "nomic-embed-text",
+ },
+ },
+
+ # Obrigatório: configuração do banco vetorial
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # Exemplo Chroma:
+ # "settings": Settings(
+ # persist_directory="/content/chroma",
+ # allow_reset=True,
+ # is_persistent=True,
+ # ),
+
+ # Exemplo Qdrant:
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # Observação: o nome da coleção é controlado pela ferramenta (padrão: "rag_tool_collection").
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/pt-BR/tools/file-document/txtsearchtool.mdx b/docs/pt-BR/tools/file-document/txtsearchtool.mdx
index cfe7c8d35..8750dc557 100644
--- a/docs/pt-BR/tools/file-document/txtsearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/txtsearchtool.mdx
@@ -57,25 +57,39 @@ Por padrão, a ferramenta utiliza o OpenAI tanto para embeddings quanto para sum
Para personalizar o modelo, você pode usar um dicionário de configuração como o exemplo a seguir:
```python Code
+from chromadb.config import Settings
+
tool = TXTSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # ou google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ # Obrigatório: provedor de embeddings + configuração
+ "embedding_model": {
+ "provider": "openai", # ou google-generativeai, cohere, ollama, ...
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...", # opcional se variável de ambiente estiver definida
+ # Exemplos por provedor:
+ # Google → model: "models/embedding-001", task_type: "retrieval_document"
+ },
+ },
+
+ # Obrigatório: configuração do banco vetorial
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # Configurações do Chroma (persistência opcional)
+ # "settings": Settings(
+ # persist_directory="/content/chroma",
+ # allow_reset=True,
+ # is_persistent=True,
+ # ),
+
+ # Exemplo de parâmetros de vetor do Qdrant:
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+
+ # Observação: o nome da coleção é controlado pela ferramenta (padrão: "rag_tool_collection").
+ }
+ },
+ }
)
```
\ No newline at end of file
diff --git a/docs/pt-BR/tools/file-document/xmlsearchtool.mdx b/docs/pt-BR/tools/file-document/xmlsearchtool.mdx
index 0777d354b..cee8e3b53 100644
--- a/docs/pt-BR/tools/file-document/xmlsearchtool.mdx
+++ b/docs/pt-BR/tools/file-document/xmlsearchtool.mdx
@@ -54,25 +54,25 @@ Este parâmetro é opcional durante a inicialização da ferramenta, mas deve se
Por padrão, a ferramenta utiliza a OpenAI tanto para embeddings quanto para sumarização. Para personalizar o modelo, você pode usar um dicionário de configuração conforme o exemplo a seguir:
```python Code
+from chromadb.config import Settings
+
tool = XMLSearchTool(
- config=dict(
- llm=dict(
- provider="ollama", # ou google, openai, anthropic, llama2, ...
- config=dict(
- model="llama2",
- # temperature=0.5,
- # top_p=1,
- # stream=true,
- ),
- ),
- embedder=dict(
- provider="google", # ou openai, ollama, ...
- config=dict(
- model="models/embedding-001",
- task_type="retrieval_document",
- # title="Embeddings",
- ),
- ),
- )
+ config={
+ "embedding_model": {
+ "provider": "openai",
+ "config": {
+ "model": "text-embedding-3-small",
+ # "api_key": "sk-...",
+ },
+ },
+ "vectordb": {
+ "provider": "chromadb", # ou "qdrant"
+ "config": {
+ # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
+ # from qdrant_client.models import VectorParams, Distance
+ # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
+ }
+ },
+ }
)
```
\ No newline at end of file