diff --git a/docs/references/http_api_reference.md b/docs/references/http_api_reference.md index e3f74b40c..0b1b7f2f2 100644 --- a/docs/references/http_api_reference.md +++ b/docs/references/http_api_reference.md @@ -2782,11 +2782,11 @@ curl --request POST \ - `"icon"`: (*Body parameter*), `string` Base64 encoding of the avatar. - `"dataset_ids"`: (*Body parameter*), `list[string]` - The IDs of the associated datasets. If omitted or set to `[]`, an empty chat assistant is created and datasets can be attached later. -- `"llm_id"`: (*Body parameter*), `string` - The chat model name. If not set, the user's default chat model will be used. -- `"llm_setting"`: (*Body parameter*), `object` - The LLM settings for the chat assistant to create. An `llm_setting` object may contain the following attributes: + The unique identifiers for the associated datasets. If omitted or set to `[]`, an empty chat assistant is created; datasets can be attached at a later time. +- `"llm_id"`: (*Body parameter*), `string` + The identifier of the chat model. If not specified, the system defaults to the user's pre-configured chat model. +- `"llm_setting"`: (*Body parameter*), `object` + A configuration object defining the LLM parameters for the assistant. The `llm_setting` object may contain the following attributes: - `"model_type"`: `string` A model type specifier. Only `"chat"` and `"image2text"` are recognized; any other inputs, or when omitted, are treated as `"chat"`. - `"temperature"`: `float` @@ -2805,7 +2805,7 @@ curl --request POST \ - `"knowledge"` is a reserved variable, which represents the retrieved chunks. - All the variables in `"system"` should be curly bracketed. - `"empty_response"`: `string` If nothing is retrieved in the dataset for the user's question, this will be used as the response. To allow the LLM to improvise when nothing is found, leave this blank. - - `"quote"`: `boolean` Indicates whether the source of text should be displayed. Defaults to `true`. + - `"quote"`: `boolean` Whether the source of text should be displayed. Defaults to `true`. - `"tts"`: `boolean` - `"refine_multiturn"`: `boolean` - `"use_kg"`: `boolean` @@ -2888,9 +2888,9 @@ Failure: **PUT** `/api/v1/chats/{chat_id}` -Replaces the persisted configuration of a specified chat assistant. +Overwrites the existing configuration for a specified chat assistant. -Use this endpoint only when you intend to send the full configuration to keep. Omitted fields are reset to server defaults. For partial updates, use `PATCH /api/v1/chats/{chat_id}` instead. +Use this endpoint only when providing a complete configuration. Any fields omitted from the request will be reset to their server-side default values. For partial updates, use `PATCH /api/v1/chats/{chat_id}` instead. #### Request @@ -2947,11 +2947,11 @@ curl --request PUT \ - `"dataset_ids"`: (*Body parameter*), `list[string]` The IDs of the associated datasets. - `"llm_id"`: (*Body parameter*), `string` - The chat model name. If not set, the user's default chat model will be used. + The chat model name. If not set, the user's default chat model is used. - `"llm_setting"`: (*Body parameter*), `object` The LLM settings for the chat assistant. An `llm_setting` object contains the following attributes: - `"model_type"`: `string` - A model type specifier. Only `"chat"` and `"image2text"` are recognized; any other inputs, or when omitted, are treated as `"chat"`. + A model type specifier. Supported values are `"chat"` and `"image2text"`. If the field is omitted or an unrecognized value is provided, it defaults to `"chat"`. - `"temperature"`: `float` Controls the randomness of the model's predictions. A lower temperature results in more conservative responses, while a higher temperature yields more creative and diverse responses. Defaults to `0.1`. - `"top_p"`: `float` @@ -2967,7 +2967,7 @@ curl --request PUT \ - `"top_k"`: (*Body parameter*), `int` - `"rerank_id"`: (*Body parameter*), `string` -Any field omitted from the request body is reset to the server-side default value for `PUT`. +For `PUT` requests, any fields omitted from the request body are reset to their server-side default values. #### Response @@ -3103,9 +3103,9 @@ Failure: **PATCH** `/api/v1/chats/{chat_id}` -Partially updates a specified chat assistant. +Performs a partial update on a specified chat assistant. -This endpoint preserves unspecified fields. Nested `llm_setting` and `prompt_config` objects are deep-merged with the existing configuration, so it is the recommended endpoint for renaming a chat assistant or updating only a subset of settings. +Unspecified fields are preserved, while nested objects, such as `llm_setting` and `prompt_config`, are deep-merged with the existing configuration. This is the recommended endpoint for renaming an assistant or modifying a specific subset of settings. #### Request @@ -3160,7 +3160,7 @@ Failure: **DELETE** `/api/v1/chats/{chat_id}` -Deletes a single chat assistant by ID. +Deletes a chat assistant by ID. #### Request diff --git a/docs/references/python_api_reference.md b/docs/references/python_api_reference.md index 7b6af60fc..8d522cc50 100644 --- a/docs/references/python_api_reference.md +++ b/docs/references/python_api_reference.md @@ -46,7 +46,7 @@ Creates a model response for the given historical chat conversation via OpenAI's #### Parameters -##### model: `str`, *Required* +##### model: `string`, *Required* The model used to generate the response. The server will parse this automatically, so you can set it to any value for now. @@ -143,18 +143,18 @@ Creates a dataset. #### Parameters -##### name: `str`, *Required* +##### name: `string`, *Required* The unique name of the dataset to create. It must adhere to the following requirements: - Maximum 128 characters. - Case-insensitive. -##### avatar: `str` +##### avatar: `string` Base64 encoding of the avatar. Defaults to `None` -##### description: `str` +##### description: `string` A brief description of the dataset to create. Defaults to `None`. @@ -166,7 +166,7 @@ Specifies who can access the dataset to create. Available options: - `"me"`: (Default) Only you can manage the dataset. - `"team"`: All team members can manage the dataset. -##### chunk_method, `str` +##### chunk_method, `string` The chunking method of the dataset to create. Available options: @@ -288,7 +288,7 @@ Specifies the page on which the datasets will be displayed. Defaults to `1`. The number of datasets on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The field by which datasets should be sorted. Available options: @@ -299,11 +299,11 @@ The field by which datasets should be sorted. Available options: Indicates whether the retrieved datasets should be sorted in descending order. Defaults to `True`. -##### id: `str` +##### id: `string` The ID of the dataset to retrieve. Defaults to `None`. -##### name: `str` +##### name: `string` The name of the dataset to retrieve. Defaults to `None`. @@ -361,7 +361,7 @@ Updates configurations for the current dataset. A dictionary representing the attributes to update, with the following keys: -- `"name"`: `str` The revised name of the dataset. +- `"name"`: `string` The revised name of the dataset. - Basic Multilingual Plane (BMP) only - Maximum 128 characters - Case-insensitive @@ -464,9 +464,9 @@ Updates configurations for the current document. A dictionary representing the attributes to update, with the following keys: -- `"display_name"`: `str` The name of the document to update. +- `"display_name"`: `string` The name of the document to update. - `"meta_fields"`: `dict[str, Any]` The meta fields of the document. -- `"chunk_method"`: `str` The parsing method to apply to the document. +- `"chunk_method"`: `string` The parsing method to apply to the document. - `"naive"`: General - `"manual`: Manual - `"qa"`: Q&A @@ -571,11 +571,11 @@ Lists documents in the current dataset. #### Parameters -##### id: `str` +##### id: `string` The ID of the document to retrieve. Defaults to `None`. -##### keywords: `str` +##### keywords: `string` The keywords used to match document titles. Defaults to `None`. @@ -587,7 +587,7 @@ Specifies the page on which the documents will be displayed. Defaults to `1`. The maximum number of documents on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The field by which documents should be sorted. Available options: @@ -618,21 +618,21 @@ A `Document` object contains the following attributes: - `chunk_method` The chunking method name. Defaults to `"naive"`. - `source_type`: The source type of the document. Defaults to `"local"`. - `type`: Type or category of the document. Defaults to `""`. Reserved for future use. -- `created_by`: `str` The creator of the document. Defaults to `""`. +- `created_by`: `string` The creator of the document. Defaults to `""`. - `size`: `int` The document size in bytes. Defaults to `0`. - `token_count`: `int` The number of tokens in the document. Defaults to `0`. - `chunk_count`: `int` The number of chunks in the document. Defaults to `0`. - `progress`: `float` The current processing progress as a percentage. Defaults to `0.0`. -- `progress_msg`: `str` A message indicating the current progress status. Defaults to `""`. +- `progress_msg`: `string` A message indicating the current progress status. Defaults to `""`. - `process_begin_at`: `datetime` The start time of document processing. Defaults to `None`. - `process_duration`: `float` Duration of the processing in seconds. Defaults to `0.0`. -- `run`: `str` The document's processing status: +- `run`: `string` The document's processing status: - `"UNSTART"` (default) - `"RUNNING"` - `"CANCEL"` - `"DONE"` - `"FAIL"` -- `status`: `str` Reserved for future use. +- `status`: `string` Reserved for future use. - `parser_config`: `ParserConfig` Configuration object for the parser. Its attributes vary based on the selected `chunk_method`: - `chunk_method`=`"naive"`: `{"chunk_token_num":128,"delimiter":"\\n","html4excel":False,"layout_recognize":True,"raptor":{"use_raptor":False}}`. @@ -862,7 +862,7 @@ Adds a chunk to the current document. #### Parameters -##### content: `str`, *Required* +##### content: `string`, *Required* The text content of the chunk. @@ -870,7 +870,7 @@ The text content of the chunk. The key terms or phrases to tag with the chunk. -##### image_base64: `str` +##### image_base64: `string` A base64-encoded image to associate with the chunk. If the chunk already has an image, the new image will be vertically concatenated below the existing one. @@ -885,16 +885,16 @@ Tag keywords to associate with the chunk. A `Chunk` object contains the following attributes: -- `id`: `str`: The chunk ID. -- `content`: `str` The text content of the chunk. +- `id`: `string`: The chunk ID. +- `content`: `string` The text content of the chunk. - `important_keywords`: `list[str]` A list of key terms or phrases tagged with the chunk. - `tag_kwd`: `list[str]` A list of tag keywords associated with the chunk. -- `image_id`: `str` The image ID associated with the chunk (empty string if no image). -- `create_time`: `str` The time when the chunk was created (added to the document). +- `image_id`: `string` The image ID associated with the chunk (empty string if no image). +- `create_time`: `string` The time when the chunk was created (added to the document). - `create_timestamp`: `float` The timestamp representing the creation time of the chunk, expressed in seconds since January 1, 1970. -- `dataset_id`: `str` The ID of the associated dataset. -- `document_name`: `str` The name of the associated document. -- `document_id`: `str` The ID of the associated document. +- `dataset_id`: `string` The ID of the associated dataset. +- `document_name`: `string` The name of the associated document. +- `document_id`: `string` The ID of the associated document. - `available`: `bool` The chunk's availability status in the dataset. Value options: - `False`: Unavailable - `True`: Available (default) @@ -934,7 +934,7 @@ Lists chunks in the current document. #### Parameters -##### keywords: `str` +##### keywords: `string` The keywords used to match chunk content. Defaults to `None` @@ -946,7 +946,7 @@ Specifies the page on which the chunks will be displayed. Defaults to `1`. The maximum number of chunks on each page. Defaults to `30`. -##### id: `str` +##### id: `string` The ID of the chunk to retrieve. Default: `None` @@ -1027,7 +1027,7 @@ Updates content or configurations for the current chunk. A dictionary representing the attributes to update, with the following keys: -- `"content"`: `str` The text content of the chunk. +- `"content"`: `string` The text content of the chunk. - `"important_keywords"`: `list[str]` A list of key terms or phrases to tag with the chunk. - `"tag_kwd"`: `list[str]` A list of tag keywords to associate with the chunk. - `"available"`: `bool` The chunk's availability status in the dataset. Value options: @@ -1065,7 +1065,7 @@ Retrieves chunks from specified datasets. #### Parameters -##### question: `str`, *Required* +##### question: `string`, *Required* The user query or query keywords. Defaults to `""`. @@ -1097,7 +1097,7 @@ The weight of vector cosine similarity. Defaults to `0.3`. If x represents the v The number of chunks engaged in vector cosine computation. Defaults to `1024`. -##### rerank_id: `str` +##### rerank_id: `string` The ID of the rerank model. Defaults to `None`. @@ -1163,13 +1163,13 @@ Creates a chat assistant. #### Parameters -##### name: `str`, *Required* +##### name: `string`, *Required* The name of the chat assistant. -##### icon: `str` +##### icon: `string` -Base64 encoding of the avatar. Defaults to `””`. +Base64 encoding of the avatar. Defaults to `""`. ##### dataset_ids: `list[str]` @@ -1181,23 +1181,23 @@ The LLM model name/ID to use. If `None`, the user’s default chat model is used ##### llm_setting: `dict | None` -LLM generation settings. Defaults to `None` (server defaults apply). Supported keys: +Configuration for LLM generation parameters. Defaults to `None` (server-side defaults apply). Supported keys: -- `”temperature”`: `float` Controls the randomness of the model’s predictions. Defaults to `0.1`. -- `”top_p”`: `float` Nucleus sampling threshold. Defaults to `0.3`. -- `”presence_penalty”`: `float` Penalizes tokens that have already appeared. Defaults to `0.4`. -- `”frequency_penalty”`: `float` Reduces repetition of frequent tokens. Defaults to `0.7`. -- `”max_token”`: `int` Maximum number of tokens in the response. Defaults to `512`. +- `"temperature"`: `float` Controls the randomness of the model's output. Higher values increase creativity, while lower values make responses more deterministic. Defaults to `0.1`. +- `"top_p"`: `float` Sets the nucleus sampling threshold. The model considers only the results of the tokens with `top_p` probability mass. Defaults to `0.3`. +- `"presence_penalty"`: `float` Penalizes tokens based on whether they have appeared in the text so far, increasing the likelihood of the model talking about new topics. Defaults to `0.4`. +- `"frequency_penalty"`: `float` Penalizes tokens based on their existing frequency in the text, decreasing the likelihood of repeating the same lines. Defaults to `0.7`. +- `"max_token"`: `int` The maximum number of tokens to generate in the response. Defaults to `512`. ##### prompt_config: `dict | None` -Instructions for the LLM to follow. Defaults to `None` (server defaults apply). Supported keys: +Instructions and behavioral settings for the LLM. Defaults to `None` (server-side defaults apply). Supported keys: -- `”system”`: `str` The system prompt content. -- `”empty_response”`: `str` Response when nothing is retrieved. Leave blank to let the LLM improvise. Defaults to `None`. -- `”prologue”`: `str` The opening greeting shown to the user. Defaults to `”Hi! I’m your assistant. What can I do for you?”`. -- `”quote”`: `bool` Whether to display source references. Defaults to `True`. -- `”parameters”`: `list[dict]` Variables used in the system prompt. Each entry has `”key”` (`str`) and `”optional”` (`bool`). The `knowledge` variable is reserved for retrieved chunks. Default: `[{“key”: “knowledge”, “optional”: True}]`. +- `"system"`: `string` The core system prompt or instructions defining the assistant's persona. +- `"empty_response"`: `string` The specific message returned when no relevant information is retrieved. If left blank, the LLM will generate its own response. Defaults to `None`. +- `"prologue"`: `string` The initial greeting displayed to the user. Defaults to `"Hi! I’m your assistant. What can I do for you?"`. +- `"quote"`: `boolean` Determines whether the assistant should include citations or source references in its responses. Defaults to `True`. +- `"parameters"`: `list[dict]` A list of variables utilized within the system prompt. Each entry must include a `"key"` (`string`) and an `"optional"` (`boolean`) status. The `knowledge` key is reserved for retrieved context chunks. Default: `[{"key": "knowledge", "optional": true}]`. #### Returns @@ -1225,37 +1225,37 @@ assistant = rag_object.create_chat("Miss R", dataset_ids=dataset_ids) Chat.update(update_message: dict) ``` -Partially updates configurations for the current chat assistant. +Performs a partial update to the configuration settings for the current chat assistant. -`Chat.update()` uses `PATCH /api/v1/chats/{chat_id}`. Only the provided keys are changed; all other fields are preserved. +`Chat.update()` utilizes the `PATCH /api/v1/chats/{chat_id}` endpoint. Only the specified keys are modified, while all other existing fields are preserved. #### Parameters ##### update_message: `dict`, *Required* -A dictionary representing the attributes to update. Supported keys: +A dictionary containing the attributes to be updated. Supported keys include: -- `”name”`: `str` The revised name of the chat assistant. -- `”icon”`: `str` Base64 encoding of the avatar. -- `”dataset_ids”`: `list[str]` The datasets to associate with the chat assistant. -- `”llm_id”`: `str` The LLM model name/ID to use. -- `”llm_setting”`: `dict` LLM generation settings: - - `”temperature”`: `float` Controls the randomness of the model’s predictions. - - `”top_p”`: `float` Nucleus sampling threshold. - - `”presence_penalty”`: `float` Penalizes tokens that have already appeared. - - `”frequency_penalty”`: `float` Reduces repetition of frequent tokens. - - `”max_token”`: `int` Maximum number of tokens in the response. -- `”prompt_config”`: `dict` Instructions for the LLM to follow: - - `”system”`: `str` The system prompt content. - - `”empty_response”`: `str` Response when nothing is retrieved. Leave blank to let the LLM improvise. - - `”prologue”`: `str` The opening greeting shown to the user. - - `”quote”`: `bool` Whether to display source references. - - `”parameters”`: `list[dict]` Variables used in the system prompt. -- `”similarity_threshold”`: `float` Minimum similarity score for retrieved chunks. Defaults to `0.2`. -- `”vector_similarity_weight”`: `float` Weight of vector cosine similarity in the hybrid score. Defaults to `0.3`. -- `”top_n”`: `int` Number of top chunks fed to the LLM. Defaults to `6`. -- `”top_k”`: `int` Candidate pool size for reranking. Defaults to `1024`. -- `”rerank_id”`: `str` Reranking model ID. If empty, vector cosine similarity is used. +- `"name"`: `string` The updated name of the chat assistant. +- `"icon"`: `string` A Base64-encoded string representing the assistant's avatar. +- `"dataset_ids"`: `list[string]` A list of unique identifiers for the datasets associated with the assistant. +- `"llm_id"`: `string` The unique identifier or name of the LLM to be used. +- `"llm_setting"`: `dict` Configuration for LLM generation parameters: + - `"temperature"`: `float` Controls the randomness of the model's output. + - `"top_p"`: `float` Sets the nucleus sampling threshold. + - `"presence_penalty"`: `float` Penalizes tokens based on whether they have already appeared in the text. + - `"frequency_penalty"`: `float` Penalizes tokens based on their existing frequency in the text. + - `"max_token"`: `int` The maximum number of tokens to generate in the response. +- `"prompt_config"`: `dict` Instructions and behavioral settings for the LLM: + - `"system"`: `string` The core system prompt or instructions defining the assistant's persona. + - `"empty_response"`: `string` The message returned when no relevant information is retrieved. Leave blank to allow the LLM to improvise. + - `"prologue"`: `string` The initial greeting displayed to the user. + - `"quote"`: `boolean` Determines whether the assistant should include citations or source references. + - `"parameters"`: `list[dict]` Variables used within the system prompt (e.g., the reserved `knowledge` key). +- `"similarity_threshold"`: `float` The minimum similarity score required for retrieved context chunks. Defaults to `0.2`. +- `"vector_similarity_weight"`: `float` The weight assigned to vector cosine similarity within the hybrid search score. Defaults to `0.3`. +- `"top_n"`: `int` The number of top-ranked chunks provided to the LLM as context. Defaults to `6`. +- `"top_k"`: `int` The size of the initial candidate pool retrieved for reranking. Defaults to `1024`. +- `"rerank_id"`: `string` The unique identifier for the reranking model. If left empty, standard vector cosine similarity is used for ranking. #### Returns @@ -1342,7 +1342,7 @@ Specifies the page on which the chat assistants will be displayed. Defaults to ` The number of chat assistants on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The attribute by which the results are sorted. Available options: @@ -1353,27 +1353,25 @@ The attribute by which the results are sorted. Available options: Indicates whether the retrieved chat assistants should be sorted in descending order. Defaults to `True`. -##### id: `str | None` +##### id: `string | None` Exact match on chat assistant ID. Defaults to `None`. -##### name: `str | None` +Filters results by the exact name of the chat assistant. Defaults to `None`. -Exact match on chat assistant name. Defaults to `None`. +##### keywords: `string | None` -##### keywords: `str | None` +Performs a case-insensitive fuzzy search against chat assistant names. Defaults to `None`. -Case-insensitive fuzzy match against chat assistant names. Defaults to `None`. +##### owner_ids: `string | list[string] | None` -##### owner_ids: `str | list[str] | None` +Filters results by one or more owner tenant IDs. Defaults to `None`. -Filter by owner tenant IDs. Defaults to `None`. +##### parser_id: `string | None` -##### parser_id: `str | None` +Filters results by a specific parser type identifier. Defaults to `None`. -Filter by parser type. Defaults to `None`. - -When `id` or `name` is provided, exact filtering takes precedence over `keywords`. +If `id` or `name` is specified, exact filtering takes precedence over the fuzzy matching provided by `keywords`. #### Returns @@ -1406,17 +1404,17 @@ Creates a session with the current chat assistant. #### Parameters -##### name: `str` +##### name: `string` The name of the chat session to create. #### Returns - Success: A `Session` object containing the following attributes: - - `id`: `str` The auto-generated unique identifier of the created session. - - `name`: `str` The name of the created session. + - `id`: `string` The auto-generated unique identifier of the created session. + - `name`: `string` The name of the created session. - `message`: `list[Message]` The opening message of the created session. Default: `[{"role": "assistant", "content": "Hi! I am your assistant, can I help you?"}]` - - `chat_id`: `str` The ID of the associated chat assistant. + - `chat_id`: `string` The ID of the associated chat assistant. - Failure: `Exception` #### Examples @@ -1446,7 +1444,7 @@ Updates the current session of the current chat assistant. A dictionary representing the attributes to update, with only one key: -- `"name"`: `str` The revised name of the session. +- `"name"`: `string` The revised name of the session. #### Returns @@ -1492,7 +1490,7 @@ Specifies the page on which the sessions will be displayed. Defaults to `1`. The number of sessions on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The field by which sessions should be sorted. Available options: @@ -1503,11 +1501,11 @@ The field by which sessions should be sorted. Available options: Indicates whether the retrieved sessions should be sorted in descending order. Defaults to `True`. -##### id: `str` +##### id: `string` The ID of the chat session to retrieve. Defaults to `None`. -##### name: `str` +##### name: `string` The name of the chat session to retrieve. Defaults to `None`. @@ -1584,7 +1582,7 @@ In streaming mode, not all responses include a reference, as this depends on the #### Parameters -##### question: `str`, *Required* +##### question: `string`, *Required* The question to start an AI-powered conversation. Default to `""` @@ -1606,11 +1604,11 @@ The parameters in prompt(system). The following shows the attributes of a `Message` object: -##### id: `str` +##### id: `string` The auto-generated message ID. -##### content: `str` +##### content: `string` The content of the message. Defaults to `"Hi! I am your assistant, can I help you?"`. @@ -1618,21 +1616,21 @@ The content of the message. Defaults to `"Hi! I am your assistant, can I help yo A list of `Chunk` objects representing references to the message, each containing the following attributes: -- `id` `str` +- `id` `string` The chunk ID. -- `content` `str` +- `content` `string` The content of the chunk. -- `img_id` `str` +- `img_id` `string` The ID of the snapshot of the chunk. Applicable only when the source of the chunk is an image, PPT, PPTX, or PDF file. -- `document_id` `str` +- `document_id` `string` The ID of the referenced document. -- `document_name` `str` +- `document_name` `string` The name of the referenced document. - `document_metadata` `dict` Optional document metadata, returned only when `extra_body.reference_metadata.include` is `true`. - `position` `list[str]` The location information of the chunk within the referenced document. -- `dataset_id` `str` +- `dataset_id` `string` The ID of the dataset to which the referenced document belongs. - `similarity` `float` A composite similarity score of the chunk ranging from `0` to `1`, with a higher value indicating greater similarity. It is the weighted sum of `vector_similarity` and `term_similarity`. @@ -1687,9 +1685,9 @@ Also supports: #### Returns - Success: A `Session` object containing the following attributes: - - `id`: `str` The auto-generated unique identifier of the created session. + - `id`: `string` The auto-generated unique identifier of the created session. - `message`: `list[Message]` The messages of the created session assistant. Default: `[{"role": "assistant", "content": "Hi! I am your assistant, can I help you?"}]` - - `agent_id`: `str` The ID of the associated agent. + - `agent_id`: `string` The ID of the associated agent. - Failure: `Exception` #### Examples @@ -1721,7 +1719,7 @@ In streaming mode, not all responses include a reference, as this depends on the #### Parameters -##### question: `str` +##### question: `string` The question to start an AI-powered conversation. If the **Begin** component takes parameters, a question is not required. @@ -1739,11 +1737,11 @@ Indicates whether to output responses in a streaming way: The following shows the attributes of a `Message` object: -##### id: `str` +##### id: `string` The auto-generated message ID. -##### content: `str` +##### content: `string` The content of the message. Defaults to `"Hi! I am your assistant, can I help you?"`. @@ -1751,21 +1749,21 @@ The content of the message. Defaults to `"Hi! I am your assistant, can I help yo A list of `Chunk` objects representing references to the message, each containing the following attributes: -- `id` `str` +- `id` `string` The chunk ID. -- `content` `str` +- `content` `string` The content of the chunk. -- `image_id` `str` +- `image_id` `string` The ID of the snapshot of the chunk. Applicable only when the source of the chunk is an image, PPT, PPTX, or PDF file. -- `document_id` `str` +- `document_id` `string` The ID of the referenced document. -- `document_name` `str` +- `document_name` `string` The name of the referenced document. - `document_metadata` `dict` Optional document metadata, returned only when `extra_body.reference_metadata.include` is `true`. - `position` `list[str]` The location information of the chunk within the referenced document. -- `dataset_id` `str` +- `dataset_id` `string` The ID of the dataset to which the referenced document belongs. - `similarity` `float` A composite similarity score of the chunk ranging from `0` to `1`, with a higher value indicating greater similarity. It is the weighted sum of `vector_similarity` and `term_similarity`. @@ -1823,7 +1821,7 @@ Specifies the page on which the sessions will be displayed. Defaults to `1`. The number of sessions on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The field by which sessions should be sorted. Available options: @@ -1834,7 +1832,7 @@ The field by which sessions should be sorted. Available options: Indicates whether the retrieved sessions should be sorted in descending order. Defaults to `True`. -##### id: `str` +##### id: `string` The ID of the agent session to retrieve. Defaults to `None`. @@ -1925,7 +1923,7 @@ Specifies the page on which the agents will be displayed. Defaults to `1`. The number of agents on each page. Defaults to `30`. -##### orderby: `str` +##### orderby: `string` The attribute by which the results are sorted. Available options: @@ -1936,11 +1934,11 @@ The attribute by which the results are sorted. Available options: Indicates whether the retrieved agents should be sorted in descending order. Defaults to `True`. -##### id: `str` +##### id: `string` The ID of the agent to retrieve. Defaults to `None`. -##### name: `str` +##### name: `string` The name of the agent to retrieve. Defaults to `None`. @@ -1974,7 +1972,7 @@ Create an agent. #### Parameters -##### title: `str` +##### title: `string` Specifies the title of the agent. @@ -1982,7 +1980,7 @@ Specifies the title of the agent. Specifies the canvas DSL of the agent. -##### description: `str` +##### description: `string` The description of the agent. Defaults to `None`. @@ -2022,11 +2020,11 @@ Update an agent. #### Parameters -##### agent_id: `str` +##### agent_id: `string` Specifies the id of the agent to be updated. -##### title: `str` +##### title: `string` Specifies the new title of the agent. `None` if you do not want to update this. @@ -2034,7 +2032,7 @@ Specifies the new title of the agent. `None` if you do not want to update this. Specifies the new canvas DSL of the agent. `None` if you do not want to update this. -##### description: `str` +##### description: `string` The new description of the agent. `None` if you do not want to update this. @@ -2072,7 +2070,7 @@ Delete an agent. #### Parameters -##### agent_id: `str` +##### agent_id: `string` Specifies the id of the agent to be deleted. @@ -2110,7 +2108,7 @@ Create a new memory. #### Parameters -##### name: `str`, *Required* +##### name: `string`, *Required* The unique name of the memory to create. It must adhere to the following requirements: @@ -2126,14 +2124,14 @@ Specifies the types of memory to extract. Available options: - `episodic`: Time-stamped records of specific events and experiences. - `procedural`: Learned skills, habits, and automated procedures. -##### embd_id: `str`, *Required* +##### embd_id: `string`, *Required* The name of the embedding model to use. For example: `"BAAI/bge-large-zh-v1.5@BAAI"` - Maximum 255 characters - Must follow `model_name@model_factory` format -##### llm_id: `str`, *Required* +##### llm_id: `string`, *Required* The name of the chat model to use. For example: `"glm-4-flash@ZHIPU-AI"` @@ -2276,11 +2274,11 @@ Specifies the page on which the datasets will be displayed. Defaults to `1` The number of memories on each page. Defaults to `50`. -##### tenant_id: `str` or `list[str]`, *Optional* +##### tenant_id: `string` or `list[str]`, *Optional* The owner's ID, supports search multiple IDs. -##### memory_type: `str` or `list[str]`, *Optional* +##### memory_type: `string` or `list[str]`, *Optional* The type of memory (as set during creation). A memory matches if its type is **included in** the provided value(s). Available options: @@ -2289,13 +2287,13 @@ The type of memory (as set during creation). A memory matches if its type is **i - `episodic` - `procedural` -##### storage_type: `str`, *Optional* +##### storage_type: `string`, *Optional* The storage format of messages. Available options: - `table`: (Default) -##### keywords: `str`, *Optional* +##### keywords: `string`, *Optional* The name of memory to retrieve, supports fuzzy search. @@ -2364,7 +2362,7 @@ Delete a specified memory. #### Parameters -##### memory_id: `str`, *Required* +##### memory_id: `string`, *Required* The ID of the memory. @@ -2401,11 +2399,11 @@ List the messages of a specified memory. #### Parameters -##### agent_id: `str` or `list[str]`, *Optional* +##### agent_id: `string` or `list[str]`, *Optional* Filters messages by the ID of their source agent. Supports multiple values. -##### keywords: `str`, *Optional* +##### keywords: `string`, *Optional* Filters messages by their session ID. This field supports fuzzy search. @@ -2461,23 +2459,23 @@ Add a message to specified memories. The IDs of the memories to save messages. -##### agent_id: `str`, *Required* +##### agent_id: `string`, *Required* The ID of the message's source agent. -##### session_id: `str`, *Required* +##### session_id: `string`, *Required* The ID of the message's session. -##### user_input: `str`, *Required* +##### user_input: `string`, *Required* The text input provided by the user. -##### agent_response: `str`, *Required* +##### agent_response: `string`, *Required* The text response generated by the AI agent. -##### user_id: `str`, *Optional* +##### user_id: `string`, *Optional* The user participating in the conversation with the agent. Defaults to `""`. @@ -2597,7 +2595,7 @@ Searches and retrieves messages from memory based on the provided `query` and ot #### Parameters -##### query: `str`, *Required* +##### query: `string`, *Required* The search term or natural language question used to find relevant messages. @@ -2605,11 +2603,11 @@ The search term or natural language question used to find relevant messages. The IDs of the memories to search. Supports multiple values. -##### agent_id: `str`, *Optional* +##### agent_id: `string`, *Optional* The ID of the message's source agent. Defaults to `None`. -##### session_id: `str`, *Optional* +##### session_id: `string`, *Optional* The ID of the message's session. Defaults to `None`. @@ -2666,11 +2664,11 @@ Retrieves the most recent messages from specified memories. Typically accepts a The IDs of the memories to search. Supports multiple values. -##### agent_id: `str`, *Optional* +##### agent_id: `string`, *Optional* The ID of the message's source agent. Defaults to `None`. -##### session_id: `str`, *Optional* +##### session_id: `string`, *Optional* The ID of the message's session. Defaults to `None`.