fix: corret imports
This commit is contained in:
Gabriel Luiz Freitas Almeida
parent
2dca6262db
commit
54d5ba78cd
2 changed files with 6 additions and 6 deletions
6
docs/static/data/AstraDB-RAG-Flows.json
vendored
6
docs/static/data/AstraDB-RAG-Flows.json
vendored
|
|
@ -375,7 +375,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInputMessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCModelComponent):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Embeddings\", name=\"embeddings\", method=\"build_embeddings\"),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInput, MessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCModelComponent):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Embeddings\", name=\"embeddings\", method=\"build_embeddings\"),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
},
|
||||
"default_headers": {
|
||||
"advanced": true,
|
||||
|
|
@ -1507,7 +1507,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInputMessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCModelComponent):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Embeddings\", name=\"embeddings\", method=\"build_embeddings\"),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.models.model import LCModelComponent\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, Output, SecretStrInput, MessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCModelComponent):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Embeddings\", name=\"embeddings\", method=\"build_embeddings\"),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
},
|
||||
"default_headers": {
|
||||
"advanced": true,
|
||||
|
|
@ -1902,7 +1902,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_text_splitters import RecursiveCharacterTextSplitter\n\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DataInput, IntInputMessageTextInput\nfrom langflow.schema import Data\nfrom langflow.template.field.base import Output\nfrom langflow.utils.util import build_loader_repr_from_data, unescape_string\n\n\nclass RecursiveCharacterTextSplitterComponent(Component):\n display_name: str = \"Recursive Character Text Splitter\"\n description: str = \"Split text into chunks of a specified length.\"\n documentation: str = \"https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter\"\n\n inputs = [\n IntInput(\n name=\"chunk_size\",\n display_name=\"Chunk Size\",\n info=\"The maximum length of each chunk.\",\n value=1000,\n ),\n IntInput(\n name=\"chunk_overlap\",\n display_name=\"Chunk Overlap\",\n info=\"The amount of overlap between chunks.\",\n value=200,\n ),\n DataInput(\n name=\"data_input\",\n display_name=\"Input\",\n info=\"The texts to split.\",\n input_types=[\"Document\", \"Data\"],\n ),\n MessageTextInput(\n name=\"separators\",\n display_name=\"Separators\",\n info='The characters to split on.\\nIf left empty defaults to [\"\\\\n\\\\n\", \"\\\\n\", \" \", \"\"].',\n is_list=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"split_data\"),\n ]\n\n def split_data(self) -> list[Data]:\n \"\"\"\n Split text into chunks of a specified length.\n\n Args:\n separators (list[str]): The characters to split on.\n chunk_size (int): The maximum length of each chunk.\n chunk_overlap (int): The amount of overlap between chunks.\n\n Returns:\n list[str]: The chunks of text.\n \"\"\"\n\n if self.separators == \"\":\n self.separators = None\n elif self.separators:\n # check if the separators list has escaped characters\n # if there are escaped characters, unescape them\n self.separators = [unescape_string(x) for x in self.separators]\n\n # Make sure chunk_size and chunk_overlap are ints\n if isinstance(self.chunk_size, str):\n self.chunk_size = int(self.chunk_size)\n if isinstance(self.chunk_overlap, str):\n self.chunk_overlap = int(self.chunk_overlap)\n splitter = RecursiveCharacterTextSplitter(\n separators=self.separators,\n chunk_size=self.chunk_size,\n chunk_overlap=self.chunk_overlap,\n )\n documents = []\n if not isinstance(self.data_input, list):\n self.data_input = [self.data_input]\n for _input in self.data_input:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n documents.append(_input)\n docs = splitter.split_documents(documents)\n data = self.to_data(docs)\n self.repr_value = build_loader_repr_from_data(data)\n return data\n"
|
||||
"value": "from langchain_text_splitters import RecursiveCharacterTextSplitter\n\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DataInput, IntInput, MessageTextInput\nfrom langflow.schema import Data\nfrom langflow.template.field.base import Output\nfrom langflow.utils.util import build_loader_repr_from_data, unescape_string\n\n\nclass RecursiveCharacterTextSplitterComponent(Component):\n display_name: str = \"Recursive Character Text Splitter\"\n description: str = \"Split text into chunks of a specified length.\"\n documentation: str = \"https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter\"\n\n inputs = [\n IntInput(\n name=\"chunk_size\",\n display_name=\"Chunk Size\",\n info=\"The maximum length of each chunk.\",\n value=1000,\n ),\n IntInput(\n name=\"chunk_overlap\",\n display_name=\"Chunk Overlap\",\n info=\"The amount of overlap between chunks.\",\n value=200,\n ),\n DataInput(\n name=\"data_input\",\n display_name=\"Input\",\n info=\"The texts to split.\",\n input_types=[\"Document\", \"Data\"],\n ),\n MessageTextInput(\n name=\"separators\",\n display_name=\"Separators\",\n info='The characters to split on.\\nIf left empty defaults to [\"\\\\n\\\\n\", \"\\\\n\", \" \", \"\"].',\n is_list=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"split_data\"),\n ]\n\n def split_data(self) -> list[Data]:\n \"\"\"\n Split text into chunks of a specified length.\n\n Args:\n separators (list[str]): The characters to split on.\n chunk_size (int): The maximum length of each chunk.\n chunk_overlap (int): The amount of overlap between chunks.\n\n Returns:\n list[str]: The chunks of text.\n \"\"\"\n\n if self.separators == \"\":\n self.separators = None\n elif self.separators:\n # check if the separators list has escaped characters\n # if there are escaped characters, unescape them\n self.separators = [unescape_string(x) for x in self.separators]\n\n # Make sure chunk_size and chunk_overlap are ints\n if isinstance(self.chunk_size, str):\n self.chunk_size = int(self.chunk_size)\n if isinstance(self.chunk_overlap, str):\n self.chunk_overlap = int(self.chunk_overlap)\n splitter = RecursiveCharacterTextSplitter(\n separators=self.separators,\n chunk_size=self.chunk_size,\n chunk_overlap=self.chunk_overlap,\n )\n documents = []\n if not isinstance(self.data_input, list):\n self.data_input = [self.data_input]\n for _input in self.data_input:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n documents.append(_input)\n docs = splitter.split_documents(documents)\n data = self.to_data(docs)\n self.repr_value = build_loader_repr_from_data(data)\n return data\n"
|
||||
},
|
||||
"data_input": {
|
||||
"advanced": false,
|
||||
|
|
|
|||
|
|
@ -679,7 +679,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, SecretStrInputMessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, SecretStrInput, MessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
},
|
||||
"default_headers": {
|
||||
"advanced": true,
|
||||
|
|
@ -1811,7 +1811,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, SecretStrInputMessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
"value": "from langchain_openai.embeddings.base import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, SecretStrInput, MessageTextInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=[\n \"text-embedding-3-small\",\n \"text-embedding-3-large\",\n \"text-embedding-ada-002\",\n ],\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\"),\n SecretStrInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\n ),\n ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n tiktoken_enabled=self.tiktoken_enable,\n default_headers=self.default_headers,\n default_query=self.default_query,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n deployment=self.deployment,\n embedding_ctx_length=self.embedding_ctx_length,\n max_retries=self.max_retries,\n model=self.model,\n model_kwargs=self.model_kwargs,\n base_url=self.openai_api_base,\n api_key=self.openai_api_key,\n openai_api_type=self.openai_api_type,\n api_version=self.openai_api_version,\n organization=self.openai_organization,\n openai_proxy=self.openai_proxy,\n timeout=self.request_timeout or None,\n show_progress_bar=self.show_progress_bar,\n skip_empty=self.skip_empty,\n tiktoken_model_name=self.tiktoken_model_name,\n )\n"
|
||||
},
|
||||
"default_headers": {
|
||||
"advanced": true,
|
||||
|
|
@ -2206,7 +2206,7 @@
|
|||
"show": true,
|
||||
"title_case": false,
|
||||
"type": "code",
|
||||
"value": "from langchain_text_splitters import RecursiveCharacterTextSplitter\n\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DataInput, IntInputMessageTextInput\nfrom langflow.schema import Data\nfrom langflow.template.field.base import Output\nfrom langflow.utils.util import build_loader_repr_from_data, unescape_string\n\n\nclass RecursiveCharacterTextSplitterComponent(Component):\n display_name: str = \"Recursive Character Text Splitter\"\n description: str = \"Split text into chunks of a specified length.\"\n documentation: str = \"https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter\"\n\n inputs = [\n IntInput(\n name=\"chunk_size\",\n display_name=\"Chunk Size\",\n info=\"The maximum length of each chunk.\",\n value=1000,\n ),\n IntInput(\n name=\"chunk_overlap\",\n display_name=\"Chunk Overlap\",\n info=\"The amount of overlap between chunks.\",\n value=200,\n ),\n DataInput(\n name=\"data_input\",\n display_name=\"Input\",\n info=\"The texts to split.\",\n input_types=[\"Document\", \"Data\"],\n ),\n MessageTextInput(\n name=\"separators\",\n display_name=\"Separators\",\n info='The characters to split on.\\nIf left empty defaults to [\"\\\\n\\\\n\", \"\\\\n\", \" \", \"\"].',\n is_list=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"split_data\"),\n ]\n\n def split_data(self) -> list[Data]:\n \"\"\"\n Split text into chunks of a specified length.\n\n Args:\n separators (list[str]): The characters to split on.\n chunk_size (int): The maximum length of each chunk.\n chunk_overlap (int): The amount of overlap between chunks.\n\n Returns:\n list[str]: The chunks of text.\n \"\"\"\n\n if self.separators == \"\":\n self.separators = None\n elif self.separators:\n # check if the separators list has escaped characters\n # if there are escaped characters, unescape them\n self.separators = [unescape_string(x) for x in self.separators]\n\n # Make sure chunk_size and chunk_overlap are ints\n if isinstance(self.chunk_size, str):\n self.chunk_size = int(self.chunk_size)\n if isinstance(self.chunk_overlap, str):\n self.chunk_overlap = int(self.chunk_overlap)\n splitter = RecursiveCharacterTextSplitter(\n separators=self.separators,\n chunk_size=self.chunk_size,\n chunk_overlap=self.chunk_overlap,\n )\n documents = []\n if not isinstance(self.data_input, list):\n self.data_input = [self.data_input]\n for _input in self.data_input:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n documents.append(_input)\n docs = splitter.split_documents(documents)\n data = self.to_data(docs)\n self.repr_value = build_loader_repr_from_data(data)\n return data\n"
|
||||
"value": "from langchain_text_splitters import RecursiveCharacterTextSplitter\n\nfrom langflow.custom import Component\nfrom langflow.inputs.inputs import DataInput, IntInput, MessageTextInput\nfrom langflow.schema import Data\nfrom langflow.template.field.base import Output\nfrom langflow.utils.util import build_loader_repr_from_data, unescape_string\n\n\nclass RecursiveCharacterTextSplitterComponent(Component):\n display_name: str = \"Recursive Character Text Splitter\"\n description: str = \"Split text into chunks of a specified length.\"\n documentation: str = \"https://docs.langflow.org/components/text-splitters#recursivecharactertextsplitter\"\n\n inputs = [\n IntInput(\n name=\"chunk_size\",\n display_name=\"Chunk Size\",\n info=\"The maximum length of each chunk.\",\n value=1000,\n ),\n IntInput(\n name=\"chunk_overlap\",\n display_name=\"Chunk Overlap\",\n info=\"The amount of overlap between chunks.\",\n value=200,\n ),\n DataInput(\n name=\"data_input\",\n display_name=\"Input\",\n info=\"The texts to split.\",\n input_types=[\"Document\", \"Data\"],\n ),\n MessageTextInput(\n name=\"separators\",\n display_name=\"Separators\",\n info='The characters to split on.\\nIf left empty defaults to [\"\\\\n\\\\n\", \"\\\\n\", \" \", \"\"].',\n is_list=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Data\", name=\"data\", method=\"split_data\"),\n ]\n\n def split_data(self) -> list[Data]:\n \"\"\"\n Split text into chunks of a specified length.\n\n Args:\n separators (list[str]): The characters to split on.\n chunk_size (int): The maximum length of each chunk.\n chunk_overlap (int): The amount of overlap between chunks.\n\n Returns:\n list[str]: The chunks of text.\n \"\"\"\n\n if self.separators == \"\":\n self.separators = None\n elif self.separators:\n # check if the separators list has escaped characters\n # if there are escaped characters, unescape them\n self.separators = [unescape_string(x) for x in self.separators]\n\n # Make sure chunk_size and chunk_overlap are ints\n if isinstance(self.chunk_size, str):\n self.chunk_size = int(self.chunk_size)\n if isinstance(self.chunk_overlap, str):\n self.chunk_overlap = int(self.chunk_overlap)\n splitter = RecursiveCharacterTextSplitter(\n separators=self.separators,\n chunk_size=self.chunk_size,\n chunk_overlap=self.chunk_overlap,\n )\n documents = []\n if not isinstance(self.data_input, list):\n self.data_input = [self.data_input]\n for _input in self.data_input:\n if isinstance(_input, Data):\n documents.append(_input.to_lc_document())\n else:\n documents.append(_input)\n docs = splitter.split_documents(documents)\n data = self.to_data(docs)\n self.repr_value = build_loader_repr_from_data(data)\n return data\n"
|
||||
},
|
||||
"data_input": {
|
||||
"advanced": false,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue