.\" Man page for llm_aggregator configuration file
.TH LLM_AGGREGATOR 5 "22 April 2026" "1.0.0" "File Formats"
.SH NAME
llm_aggregator.conf \- configuration file for llm_aggregator
.SH DESCRIPTION
The
.B llm_aggregator
configuration file is a TOML file that allows users to set default values
for all command\-line options. This eliminates the need to specify common
options on every invocation.
.PP
The configuration file is read from:
.PP
.RS 4
~/.config/llm_aggregator/config.toml
.RE
.PP
If the file does not exist, default values are used for all options.
Configuration options can still be overridden by environment variables and
command\-line arguments.
.SH FILE STRUCTURE
The configuration file is a TOML file with the following sections and
options:
.SH "[feed_aggregation]"
Options controlling how feeds are fetched and processed.
.TP
.B max_articles_per_feed = \fIinteger\fR
Maximum number of articles to fetch from each feed.
.br
Default: 10
.TP
.B max_days_old = \fIinteger\fR
Only include articles from the last N days. Set to 0 to include all articles
regardless of age.
.br
Default: 7
.TP
.B max_total_articles = \fIinteger\fR
Maximum total number of articles to process across all feeds.
.br
Default: 20
.SH "[filtering]"
Options for filtering article content by keywords.
.TP
.B include_keywords = \fI"string"\fR
Comma\-separated list of keywords to include. Only articles containing at
least one of these keywords (case\-insensitive) will be processed.
.br
Example: include_keywords = "linux,opensource"
.TP
.B exclude_keywords = \fI"string"\fR
Comma\-separated list of keywords to exclude. Any article containing one of
these keywords (case\-insensitive) will be filtered out.
.br
Example: exclude_keywords = "windows,microsoft"
.SH "[llm_api]"
Options for the LLM API connection and behaviour.
.TP
.B api_key = \fI"string"\fR
OpenAI\-compatible API key. Can also be set via the
.B LLM_AGGREGATOR_API_KEY
environment variable.
.br
Note: It is generally safer to set this via the environment variable rather
than in the configuration file.
.TP
.B base_url = \fI"string"\fR
API base URL for the LLM service.
.br
Default: "https://api.deepseek.com"
.br
Example for local Ollama: "http://localhost:11434/v1"
.TP
.B model = \fI"string"\fR
LLM model to use for summarisation.
.br
Default: "deepseek-chat"
.br
Common models: deepseek-chat, deepseek-reasoner, gpt-4o, llama3
.TP
.B max_tokens = \fIinteger\fR
Maximum number of tokens in the LLM response.
.br
Default: 4000
.TP
.B temperature = \fIfloat\fR
Sampling temperature for the LLM. Must be between 0.0 and 1.0.
.br
Lower values produce more deterministic output, higher values produce more
creative output.
.br
Default: 0.7
.SH "[system]"
Options related to the LLM system prompt.
.TP
.B system_prompt = \fI"string"\fR
Custom system prompt for the LLM. The system prompt instructs the AI on
how to behave and what format to use in its responses.
.br
.br
Default:
.br
.nf
  "You are an expert analyst and summariser.
   You analyse content from multiple sources and provide
   concise, insightful summaries based on user requests.
   Focus on key points, trends, and important information."
.fi
.br
.br
The system prompt can span multiple lines using TOML's multi\-line string
syntax (triple quotes).
.SH "[output]"
Options for controlling output format and destination.
.TP
.B output = \fI"string"\fR
Output format. Must be one of: "text", "json", or "markdown".
.br
Default: "text"
.TP
.B output_file = \fI"string"\fR
Optional file path to write output to. If not specified, output is written
to stdout.
.br
Example: output_file = "/tmp/summary.txt"
.TP
.B include_articles = \fIboolean\fR
Include the original articles in JSON output. Only applicable when
.B output
is set to "json".
.br
Default: false
.SH EXAMPLE CONFIGURATION
Below is a complete example configuration file:
.PP
.RS 4
.nf
# llm_aggregator configuration file
# Location: ~/.config/llm_aggregator/config.toml

# Feed aggregation options
max_articles_per_feed = 10
max_days_old = 7
max_total_articles = 20

# Content filtering (comma-separated keywords)
# include_keywords = "linux,opensource"
# exclude_keywords = "windows,microsoft"

# LLM API options
# api_key = "your_api_key_here"  # Can also be set via LLM_AGGREGATOR_API_KEY env var
model = "deepseek-chat"
max_tokens = 4000
temperature = 0.7

# System prompt for LLM API
system_prompt = """You are an expert analyst and summariser.
You analyse content from multiple sources and provide
concise, insightful summaries based on user requests.
Focus on key points, trends, and important information."""

# Output options
output = "text"  # Options: text, json, markdown
# output_file = ""  # Optional output file path
include_articles = false
.fi
.RE
.PP
A more feature\-rich example with filtering and custom API settings:
.PP
.RS 4
.nf
# Feed aggregation options
max_articles_per_feed = 15
max_days_old = 3
max_total_articles = 30

# Content filtering
include_keywords = "linux,kernel,open source,AI"
exclude_keywords = "windows, proprietary"

# LLM API options
# api_key = "sk-..."  # Use env var in production
base_url = "https://api.deepseek.com"
model = "deepseek-chat"
max_tokens = 6000
temperature = 0.5

# Custom system prompt for technical content analysis
system_prompt = """You are a technical analyst specialising in
open source software and cybersecurity. Provide detailed,
accurate summaries focusing on technical implications
and practical applications."""

# Output options
output = "markdown"
include_articles = true
.fi
.RE
.SH CONFIGURATION PRECEDENCE
Configuration options are resolved in the following order (highest to lowest):
.TP 2
1.
Command\-line arguments (e.g., \-\-model, \-\-output)
.TP 2
2.
Environment variables (e.g., LLM_AGGREGATOR_MODEL, LLM_AGGREGATOR_OUTPUT)
.TP 2
3.
Configuration file (~/.config/llm_aggregator/config.toml)
.TP 2
4.
Built\-in defaults
.PP
This means any option specified on the command line will override both the
environment variable and the configuration file for that invocation.
.SH ENVIRONMENT VARIABLES
The following environment variables can be used to set configuration options.
They take precedence over the configuration file but not over command\-line
arguments.
.TP
.B LLM_AGGREGATOR_API_KEY
API key for the LLM service.
.TP
.B LLM_AGGREGATOR_BASE_URL
API base URL.
.TP
.B LLM_AGGREGATOR_MODEL
Model name.
.TP
.B LLM_AGGREGATOR_MAX_TOKENS
Maximum tokens in response.
.TP
.B LLM_AGGREGATOR_TEMPERATURE
Sampling temperature.
.TP
.B LLM_AGGREGATOR_SYSTEM_PROMPT
Custom system prompt.
.TP
.B LLM_AGGREGATOR_MAX_ARTICLES_PER_FEED
Maximum articles per feed.
.TP
.B LLM_AGGREGATOR_MAX_DAYS_OLD
Maximum article age in days.
.TP
.B LLM_AGGREGATOR_MAX_TOTAL_ARTICLES
Maximum total articles.
.TP
.B LLM_AGGREGATOR_INCLUDE_KEYWORDS
Comma\-separated include keywords.
.TP
.B LLM_AGGREGATOR_EXCLUDE_KEYWORDS
Comma\-separated exclude keywords.
.TP
.B LLM_AGGREGATOR_OUTPUT
Output format (text/json/markdown).
.TP
.B LLM_AGGREGATOR_OUTPUT_FILE
Output file path.
.TP
.B LLM_AGGREGATOR_INCLUDE_ARTICLES
Include articles in JSON output (true/false).
.SH SECURITY CONSIDERATIONS
.TP 2
\(bu
Avoid storing API keys in the configuration file. Use the
.B LLM_AGGREGATOR_API_KEY
environment variable instead.
.TP 2
\(bu
The configuration file should have restrictive permissions (mode 600) to
prevent other users from reading your API key if it is stored in the file.
.TP 2
\(bu
Command\-line arguments may be visible to other users via process listings.
Use environment variables for sensitive data in shared environments.
.SH FILES
.TP
.B ~/.config/llm_aggregator/config.toml
Primary configuration file location.
.TP
.B /etc/llm_aggregator/config.toml
System\-wide configuration (if applicable).
.SH SEE ALSO
.BR llm_aggregator (1)
.SH AUTHOR
Written by Maxwell Jensen.
.SH REPORTING BUGS
Report bugs at: https://codeberg.org/maxwelljensen/llm_aggregator/issues
.SH COPYRIGHT
Copyright \(co 2026 Maxwell Jensen.
.br
Licensed under the European Union Public Licence 1.2 (EUPL\-1.2).
.br
See
.BR LICENCE.txt
for full licence details.