mirror of
https://github.com/MindWorkAI/AI-Studio.git
synced 2026-10-17 11:37:59 +00:00
improved chunking pipeline and handling of expert settings
This commit is contained in:
1 parent
2829051e4c
commit
89f7156fdf
16 files changed
+764
-138
No files matched your search
@@ -3817,6 +3817,12 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCEERIV1USERNAMEPASSWORDEXPORTDIALOG:
|
||||
-- Cancel
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCEERIV1USERNAMEPASSWORDEXPORTDIALOG::T900713019"] = "Cancel"
|
||||
|
||||
-- Hide Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1108876344"] = "Hide Expert Settings"
|
||||
|
||||
-- Optional expert settings for how this data source is split before embedding.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1133561850"] = "Optional expert settings for how this data source is split before embedding."
|
||||
|
||||
-- Describe what data this directory contains to help the AI select it.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1136409150"] = "Describe what data this directory contains to help the AI select it."
|
||||
|
||||
@@ -3826,6 +3832,9 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1265737624"
|
||||
-- Selected base directory for this data source
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1312296210"] = "Selected base directory for this data source"
|
||||
|
||||
-- Maximum number of tokens per chunk for this data source. Use 0 to use the embedding provider setting.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1529596777"] = "Maximum number of tokens per chunk for this data source. Use 0 to use the embedding provider setting."
|
||||
|
||||
-- Description
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1725856265"] = "Description"
|
||||
|
||||
@@ -3838,24 +3847,48 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1847791252"
|
||||
-- In order for the AI to be able to determine the appropriate data at any time, you must choose an embedding method.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T1948697886"] = "In order for the AI to be able to determine the appropriate data at any time, you must choose an embedding method."
|
||||
|
||||
-- The data source max chunk length must be less than or equal to the embedding provider limit ({0}).
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2166221195"] = "The data source max chunk length must be less than or equal to the embedding provider limit ({0})."
|
||||
|
||||
-- Number of tokens repeated at the start of the next chunk. Use 0 to disable overlap.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2263831524"] = "Number of tokens repeated at the start of the next chunk. Use 0 to disable overlap."
|
||||
|
||||
-- Add
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2646845972"] = "Add"
|
||||
|
||||
-- Chunk overlap length
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2801813827"] = "Chunk overlap length"
|
||||
|
||||
-- The embedding you selected runs locally or in your organization. Your data is not sent to the cloud.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2814869210"] = "The embedding you selected runs locally or in your organization. Your data is not sent to the cloud."
|
||||
|
||||
-- Embedding
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T2838542994"] = "Embedding"
|
||||
|
||||
-- Please enter 0 or a positive max chunk length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T3130373769"] = "Please enter 0 or a positive max chunk length."
|
||||
|
||||
-- Please enter 0 or a positive overlap length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T3242265813"] = "Please enter 0 or a positive overlap length."
|
||||
|
||||
-- For some data types, such as Office files, MindWork AI Studio requires the open-source application Pandoc.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T3359366900"] = "For some data types, such as Office files, MindWork AI Studio requires the open-source application Pandoc."
|
||||
|
||||
-- Show Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T3361153305"] = "Show Expert Settings"
|
||||
|
||||
-- Max chunk length
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T3621670500"] = "Max chunk length"
|
||||
|
||||
-- Your security policy
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T4081226330"] = "Your security policy"
|
||||
|
||||
-- Select the base directory
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T562479068"] = "Select the base directory"
|
||||
|
||||
-- The overlap must be smaller than the effective max chunk length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T57492807"] = "The overlap must be smaller than the effective max chunk length."
|
||||
|
||||
-- Data Source Name
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYDIALOG::T813773421"] = "Data Source Name"
|
||||
|
||||
@@ -3934,9 +3967,18 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYINFODIALOG::T4438734
|
||||
-- The directory chosen for the data source exists.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALDIRECTORYINFODIALOG::T445858624"] = "The directory chosen for the data source exists."
|
||||
|
||||
-- Hide Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1108876344"] = "Hide Expert Settings"
|
||||
|
||||
-- Optional expert settings for how this data source is split before embedding.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1133561850"] = "Optional expert settings for how this data source is split before embedding."
|
||||
|
||||
-- Select a file for this data source. The content of this file will be processed for the data source.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1190880267"] = "Select a file for this data source. The content of this file will be processed for the data source."
|
||||
|
||||
-- Maximum number of tokens per chunk for this data source. Use 0 to use the embedding provider setting.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1529596777"] = "Maximum number of tokens per chunk for this data source. Use 0 to use the embedding provider setting."
|
||||
|
||||
-- Description
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1725856265"] = "Description"
|
||||
|
||||
@@ -3949,9 +3991,18 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1847791252"] = "
|
||||
-- In order for the AI to be able to determine the appropriate data at any time, you must choose an embedding method.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T1948697886"] = "In order for the AI to be able to determine the appropriate data at any time, you must choose an embedding method."
|
||||
|
||||
-- The data source max chunk length must be less than or equal to the embedding provider limit ({0}).
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2166221195"] = "The data source max chunk length must be less than or equal to the embedding provider limit ({0})."
|
||||
|
||||
-- Number of tokens repeated at the start of the next chunk. Use 0 to disable overlap.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2263831524"] = "Number of tokens repeated at the start of the next chunk. Use 0 to disable overlap."
|
||||
|
||||
-- Add
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2646845972"] = "Add"
|
||||
|
||||
-- Chunk overlap length
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2801813827"] = "Chunk overlap length"
|
||||
|
||||
-- The embedding you selected runs locally or in your organization. Your data is not sent to the cloud.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2814869210"] = "The embedding you selected runs locally or in your organization. Your data is not sent to the cloud."
|
||||
|
||||
@@ -3961,15 +4012,30 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2838542994"] = "
|
||||
-- Describe what data this file contains to help the AI select it.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T2859265837"] = "Describe what data this file contains to help the AI select it."
|
||||
|
||||
-- Please enter 0 or a positive max chunk length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3130373769"] = "Please enter 0 or a positive max chunk length."
|
||||
|
||||
-- Please enter 0 or a positive overlap length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3242265813"] = "Please enter 0 or a positive overlap length."
|
||||
|
||||
-- For some data types, such as Office files, MindWork AI Studio requires the open-source application Pandoc.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3359366900"] = "For some data types, such as Office files, MindWork AI Studio requires the open-source application Pandoc."
|
||||
|
||||
-- Show Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3361153305"] = "Show Expert Settings"
|
||||
|
||||
-- Max chunk length
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3621670500"] = "Max chunk length"
|
||||
|
||||
-- Select the file
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T3740148848"] = "Select the file"
|
||||
|
||||
-- Your security policy
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T4081226330"] = "Your security policy"
|
||||
|
||||
-- The overlap must be smaller than the effective max chunk length.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T57492807"] = "The overlap must be smaller than the effective max chunk length."
|
||||
|
||||
-- Data Source Name
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::DATASOURCELOCALFILEDIALOG::T813773421"] = "Data Source Name"
|
||||
|
||||
@@ -4132,12 +4198,18 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGMETHODDIALOG::T662524223"] = "A lin
|
||||
-- Cancel
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGMETHODDIALOG::T900713019"] = "Cancel"
|
||||
|
||||
-- Hide Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1108876344"] = "Hide Expert Settings"
|
||||
|
||||
-- Failed to store the API key in the operating system. The message was: {0}. Please try again.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1122745046"] = "Failed to store the API key in the operating system. The message was: {0}. Please try again."
|
||||
|
||||
-- API Key
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1324664716"] = "API Key"
|
||||
|
||||
-- Please be aware: This section is for experts only. For cloud providers, the selected tokenizer and chunk settings may not match the real embedding model limits exactly.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1345053261"] = "Please be aware: This section is for experts only. For cloud providers, the selected tokenizer and chunk settings may not match the real embedding model limits exactly."
|
||||
|
||||
-- Create account
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1356621346"] = "Create account"
|
||||
|
||||
@@ -4159,18 +4231,21 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1847791252"] = "Up
|
||||
-- Failed to load the API key from the operating system. The message was: {0}. You might ignore this message and provide the API key again.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T1870831108"] = "Failed to load the API key from the operating system. The message was: {0}. You might ignore this message and provide the API key again."
|
||||
|
||||
-- Maximum number of tokens sent to the embedding model per chunk. The default is 16,384.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2064265557"] = "Maximum number of tokens sent to the embedding model per chunk. The default is 16,384."
|
||||
|
||||
-- Model
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2189814010"] = "Model"
|
||||
|
||||
-- Embedding batch size
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2209963239"] = "Embedding batch size"
|
||||
|
||||
-- (Optional) API Key
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2331453405"] = "(Optional) API Key"
|
||||
|
||||
-- Invalid tokenizer:
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2448302543"] = "Invalid tokenizer:"
|
||||
|
||||
-- Maximum number of tokens sent to the embedding model per chunk.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2544519277"] = "Maximum number of tokens sent to the embedding model per chunk."
|
||||
|
||||
-- Add
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2646845972"] = "Add"
|
||||
|
||||
@@ -4192,12 +4267,15 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T2961294165"] = "To
|
||||
-- Please enter a token limit greater than 0.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T3316544737"] = "Please enter a token limit greater than 0."
|
||||
|
||||
-- Show Expert Settings
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T3361153305"] = "Show Expert Settings"
|
||||
|
||||
-- How many chunks are sent to the embedding provider at once. The default is 1.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T3780233303"] = "How many chunks are sent to the embedding provider at once. The default is 1."
|
||||
|
||||
-- Choose a custom tokenizer here
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T3787466119"] = "Choose a custom tokenizer here"
|
||||
|
||||
-- For better embeddings and less storage usage, it's recommended to use a custom tokenizer to enable a more accurate token count.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T4126312157"] = "For better embeddings and less storage usage, it's recommended to use a custom tokenizer to enable a more accurate token count."
|
||||
|
||||
-- Model selection
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T416738168"] = "Model selection"
|
||||
|
||||
@@ -4207,6 +4285,9 @@ UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T504465522"] = "We
|
||||
-- Host
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T808120719"] = "Host"
|
||||
|
||||
-- Please enter an embedding batch size greater than 0.
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T840259907"] = "Please enter an embedding batch size greater than 0."
|
||||
|
||||
-- Provider
|
||||
UI_TEXT_CONTENT["AISTUDIO::DIALOGS::EMBEDDINGPROVIDERDIALOG::T900237532"] = "Provider"
|
||||
|
||||
|
||||
Reference in new issue
Block a user