Summarize Operator

The Summarize LOP leverages AI models to generate summaries of conversations, tables, or text. It supports various summary types (brief, detailed, bullet points, action items) and integrates with different AI API servers (OpenRouter, OpenAI, Groq, Ollama, LM Studio, Custom) for model selection. This operator is particularly useful for quickly condensing large amounts of information into digestible formats, aiding in decision-making and information retrieval.

Requirements

• Python Packages: Required based on selected API server (e.g., openai).
• ChatTD Operator: Required and must be configured.

Input/Output

Inputs

• Conversation (Table DAT): Requires role and message columns.
• Table (Table DAT): Generic table data.
• Text (Text DAT): Plain text content.

Outputs

• Summary (Text DAT): Contains the generated summary.

Parameters

Summary Page

Summary (Summary) op('summarize').par.Summary Str

Default:

"" (Empty String)

Summary Type (Summarytype) op('summarize').par.Summarytype Menu

Default:

brief

Options:

brief, detailed, bullet_points, action_items

Input Type (Inputtype) op('summarize').par.Inputtype Menu

Default:

conversation

Options:

conversation, table, text

Custom Prompt (Customprompt) op('summarize').par.Customprompt Str

Default:

None

Auto Call Summary (Autocall) op('summarize').par.Autocall Toggle

Default:

false

Active (Active) op('summarize').par.Active Toggle

Default:

false

Call Summary (Call) op('summarize').par.Call Pulse

Default:

None

JSON Mode (Jsonmode) op('summarize').par.Jsonmode Toggle

Default:

false

Header

Model Page

Output Settings Header

Max Tokens (Maxtokens) op('summarize').par.Maxtokens Int

Default:

256

Temperature (Temperature) op('summarize').par.Temperature Float

Default:

0.0

Model Selection Header

Use Model From (Modelselection) op('summarize').par.Modelselection Menu

Default:

chattd_model

Options:

chattd_model, custom_model, controller_model

Controller [ Model ] (Modelcontroller) op('summarize').par.Modelcontroller OP

Default:

None

Select API Server (Apiserver) op('summarize').par.Apiserver Menu

Default:

openrouter

Options:

openrouter, openai, groq, ollama, lmstudio, custom

AI Model (Model) op('summarize').par.Model Menu

Default:

llama-3.2-11b-vision-preview

Search (Search) op('summarize').par.Search Toggle

Default:

false

Model Search (Modelsearch) op('summarize').par.Modelsearch Str

Default:

None

Callbacks Page

Callbacks Header

Callback DAT (Callbackdat) op('summarize').par.Callbackdat DAT

Default:

ChatTD_callbacks

Edit Callbacks (Editcallbacksscript) op('summarize').par.Editcallbacksscript Pulse

Default:

None

Create Callbacks (Createpulse) op('summarize').par.Createpulse Pulse

Default:

None

onSummaryComplete (Onsummarycomplete) op('summarize').par.Onsummarycomplete Toggle

Default:

false

Textport Debug Callbacks (Debugcallbacks) op('summarize').par.Debugcallbacks Menu

Default:

Full Details

Options:

None, Errors Only, Basic Info, Full Details

About Page

Show Built In Pars (Showbuiltin) op('summarize').par.Showbuiltin Toggle

Default:

false

Version (Version) op('summarize').par.Version String

Default:

None

Last Updated (Lastupdated) op('summarize').par.Lastupdated String

Default:

None

Chattd (Chattd) op('summarize').par.Chattd OP

Default:

None

Creator (Creator) op('summarize').par.Creator String

Default:

None

Website (Website) op('summarize').par.Website String

Default:

None

Bypass (Bypass) op('summarize').par.Bypass Toggle

Default:

false

Callbacks

Available Callbacks:

• onSummaryComplete

Example Callback Structure:

def onSummaryComplete(info):
# Called when the summarization process finishes successfully
# info dictionary contains details like:
# - op: The Summarize operator
# - summary: The generated summary text
# - inputType: 'conversation', 'table', or 'text'
print(f"Summary generated: {info.get('summary')[:50]}...")
# Example: op('summary_display_text').text = info.get('summary')
pass

Performance Considerations

• Max Tokens affects summary length and processing time.
• Model choice impacts speed and quality; experiment with different providers/models.

Usage Examples

Summarizing a Conversation

summarize_op = op('summarize1')
conv_dat = op('conversation_log') # Table DAT with role, message cols

summarize_op.inputConnectors[0].connect(conv_dat)
summarize_op.par.Inputtype = 'conversation'
summarize_op.par.Summarytype = 'brief'
summarize_op.par.Call.pulse()

# Summary result in summarize_op.op('summary_dat')

Using a Custom Prompt for Table Summary

summarize_op = op('summarize1')
table_dat = op('sales_data')

summarize_op.inputConnectors[1].connect(table_dat) # Connect to Table input
s summarize_op.par.Inputtype = 'table'
summarize_op.par.Summarytype = 'bullet points'
s summarize_op.par.Customprompt = "Summarize the key sales trends from this table."
summarize_op.par.Call.pulse()

Common Use Cases

• Condensing meeting transcripts.
• Extracting key info from data tables.
• Summarizing customer feedback.
• Creating executive summaries of reports.
• Automating news article summarization.