AI Analysis Push

TrendRadar can connect to AI large language models to automatically analyze the trending topics it collects and generate an insight report attached to the push message. Once enabled, what you receive is no longer just a list of headlines, but an intelligence brief with in-depth analysis.

Three AI features at a glance

TrendRadar offers three independent AI features: Analysis (in-depth insight reports), Filtering (smart classification replacing keywords), and Translation (multilingual title translation). All three share the same ai section for model configuration (api_key, model, etc.) and can be enabled in any combination without depending on each other. The Translation feature only translates news titles — it does not translate AI analysis report content.

The five sections of AI analysis

The AI analyzes your trending topics in depth across the following five sections:

1. Core trends & sentiment landscape (core_trends) : automatically reads every trending topic that matches your keywords and distills the topics drawing the most attention right now along with the overall sentiment landscape.

2. Sentiment direction & controversy (sentiment_controversy) : analyzes the emotional direction, the distribution of opinions, and the focal points of controversy in public discussion, helping you grasp where public sentiment is heading.

3. Anomalies & weak signals (signals) : surfaces unusual fluctuations and emerging weak signals, catching early signs of events that may grow into significant developments.

4. RSS deep insights (rss_insights) : performs in-depth analysis on RSS feed content, extracting valuable information and trends.

5. Outlook & strategic recommendations (outlook_strategy) : synthesizes an overall assessment of how trending events may develop and provides strategic recommendations and actionable suggestions.

How to enable

Enabling AI analysis requires the following three mandatory settings. Start by checking the fields in config/config.yaml. Docker and GitHub Actions can override them with environment variables; store API keys in GitHub Actions Secrets rather than committing them.

Required configuration

config.yaml field	Environment override	Example value	Description
config.yaml field	Environment override	Example value	Description
`ai_analysis.enabled`	`AI_ANALYSIS_ENABLED`	true	Master switch for enabling AI analysis
`ai.api_key`	`AI_API_KEY`	sk-xxxxxx	Your AI service API key
`ai.model`	`AI_MODEL`	openai/deepseek-v4-flash	Model identifier (format: provider/model-name)

The fragment below only shows where the fields belong. Edit the existing ai and ai_analysis sections in config/config.yaml one field at a time:

Do not paste this whole block, replace config.yaml, or add a second ai section

Keep every other setting in your existing config.yaml and change only the matching fields. Duplicate YAML sections, incorrect indentation, or replacing the entire file can disable configuration or prevent the application from starting.

ai:
  model: "openai/deepseek-v4-flash"
  api_key: "sk-xxxxxx"
  api_base: "https://api.deepseek.com"
  timeout: 120
  temperature: 1.0
  max_tokens: 5000
  num_retries: 1
  fallback_models: []

ai_analysis:
  enabled: true
  language: "Chinese"

Model identifier format

ai.model (or AI_MODEL) must contain a slash and use the provider-prefix/model-ID form. The prefix tells LiteLLM which protocol to use, while the model ID must exactly match what the provider or relay accepts—not merely a display name shown in its dashboard.

Choose an integration mode first

Most relays—and many official model APIs—expose an OpenAI-compatible endpoint. Prefer the first mode: it requires only the exact model ID, API key, and API base URL, without first looking up a LiteLLM provider name. Use LiteLLM provider mode only when the compatible route does not work or a dedicated adapter is required.

Integration mode	ai.model / AI_MODEL example	Notes
OpenAI-compatible API (recommended)	`openai/<exact endpoint model ID>`	Set api_base; works with most relays and official services that expose a compatible API
LiteLLM provider mode (fallback)	`<provider prefix>/<model ID>`	If the compatible route fails, look up the provider prefix in LiteLLM documentation
Ollama (local deployment)	`ollama_chat/<local model name>`	Set api_base; TrendRadar requires any non-empty placeholder api_key

Integration configuration examples

The four tabs below cover common setup scenarios. The first two use DeepSeek to demonstrate cloud API patterns; local Ollama and deployment-time environment overrides are explained separately.

OpenAI-compatible API

LiteLLM provider mode

Local Ollama

Environment variables / Secrets

DeepSeek example

Prefixing the model ID with openai/ forces LiteLLM to send an OpenAI Chat Completions request to api_base. The address and model ID below come from the official DeepSeek API documentation:

ai:
  model: "openai/deepseek-v4-flash"
  api_key: "<DeepSeek API key>"
  api_base: "https://api.deepseek.com"

For a relay, replace only three values

Keep the openai/ prefix and replace the model ID after it, the API key, and api_base with the values from the relay. Whether the base URL includes /v1 depends on that relay's documentation. DeepSeek's current Quick Start uses https://api.deepseek.com, while https://api.deepseek.com/v1 remains compatible; this guide follows the current official example. Never append /chat/completions to either base URL.

Partner integration examples

The following optional model services are provided by project partners. They follow the same configuration rules described above, so choose one only when it fits your needs.

Partner

One OpenAI-compatible model configuration powers TrendRadar analysis, smart filtering, and headline translation.

Start with a model and an API keyChoose a text model, then sign in to the console to create an API key.

1. Choose model 2. Create API key

New users should register first, create and save a key on the API Keys page, and check their balance before making requests.

Configure TrendRadar

Update these fields in your existing config/config.yaml, keeping all other settings. Do not add duplicate ai or ai_analysis sections.

ai:
  model: "openai/deepseek-v4-flash"
  api_key: "<ApiSmart API Key>"
  api_base: "https://gw.apismart.ai/v1"

ai_analysis:
  enabled: true

Model ID

The example deepseek-v4-flash comes from the official API guide. Keep the openai/ prefix and use the exact text model ID, including case, punctuation, and version.

API base URL

Use the base URL above, keeping /v1 without appending /chat/completions. Image and video models are not used for news analysis.

Docker / GitHub Actions environment variables

Model discovery and access

Partner

Connect a text model through DeepSider API’s OpenAI-compatible interface. The same configuration supports TrendRadar analysis, smart filtering, and headline translation.

Choose a model and create an API keyCheck API Usage in the model details for Chat Completions support, then create a key with access to that model.

1. Choose model 2. Create API key

Register and sign in, create a token on the API Keys page, select a group with model access, and copy the full key. Check both account credit and token quota before calling. See the authentication guide.

Configure TrendRadar

Update these fields in your existing config/config.yaml and keep all other settings. Do not add duplicate ai or ai_analysis sections. Replace both the model ID and API key placeholders before use.

ai:
  model: "openai/YOUR_CHAT_MODEL"
  api_key: "<DeepSider API Key>"
  api_base: "https://www.deepsiderapi.com/v1"

ai_analysis:
  enabled: true

Model ID

Keep openai/ and replace YOUR_CHAT_MODEL with an exact Chat Completions model ID available to your key. Match its case, punctuation, and version. Image and video models are unsuitable for news analysis.

API base URL

Use the www address above with a single /v1 suffix. Do not append /chat/completions. The endpoint follows the official quickstart.

Docker / GitHub Actions environment variables

Find model IDs and troubleshoot requests

Partner

Volcengine Ark supports both an OpenAI-compatible endpoint and LiteLLM provider mode. Both use an Ark API key:

Integration mode	ai.model / AI_MODEL	ai.api_base / AI_API_BASE
Integration mode	ai.model / AI_MODEL	ai.api_base / AI_API_BASE
OpenAI-compatible (recommended)	`openai/doubao-seed-2-1-pro-260628`	`https://ark.cn-beijing.volces.com/api/v3`
LiteLLM Volcengine (fallback)	`volcengine/doubao-seed-2-1-pro-260628`	Empty (uses the default endpoint)

The example uses Doubao Seed 2.1 Pro. You may replace it with another exact model ID from the console, such as deepseek-v4-flash-260425, or with an Endpoint ID for a custom inference endpoint. Use an Ark API key, not an IAM Access Key / Secret Key pair.

More official resources (optional)

This integration guide is sponsored by Volcengine.Partnership details and offer

Optional configuration

The settings below all have sensible defaults and usually don't need to be changed. If you have special needs (for example using a proxy or adjusting the output length), set them as needed.

Optional settings

Configuration field	Default	Description
Configuration field	Default	Description
`ai.api_base`	Empty	API base URL; follow the service docs on whether /v1 is required, never append /chat/completions; AI_API_BASE can override it
`ai.temperature`	1.0	Sampling temperature (0-2); configurable only in config.yaml
`ai.max_tokens`	5000	Maximum generated tokens; set to 0 to omit max_tokens from the provider request
`ai.timeout`	120	Request timeout in seconds; AI_TIMEOUT can override it
`ai.num_retries`	1	Retries after a failed request; configurable only in config.yaml
`ai.fallback_models`	[]	Backup models tried in order when the primary model fails

ai_analysis section settings

The following settings are configured in the ai_analysis section of config.yaml, controlling the content and scope of the analysis report.

Configuration field	Default	Description
Configuration field	Default	Description
`language`	Chinese	Output language of the analysis report
`max_news_for_analysis`	150	Maximum number of news items included in the analysis (controls token cost)
`include_rss`	false	Whether to include RSS content in the analysis
`include_standalone`	true	Whether to include standalone display section data
`include_rank_timeline`	true	Rank timeline detail level (true = full trajectory, false = simplified format to save tokens)

Automatic model fallback (fallback_models)

You can configure a fallback_models list in config.yaml. When a request to the primary model fails, the system tries the backup models in order. The current implementation shares the same api_key and api_base with every fallback. With a relay, for example, use ["openai/model-b", "openai/model-c"]. If fallbacks belong to different providers with different keys, route them through one compatible gateway first; a single shared TrendRadar configuration cannot supply a separate key for each provider.

Push modes

Once AI analysis is enabled, you can choose what the push message contains:

both (news + AI analysis)

only_analysis (AI analysis only)

The push message contains both the news list and the AI analysis report. This is the default mode and suits most users.

push:
  mode: both    # news list + AI analysis report

Analysis modes

AI analysis supports four modes, each with a different analysis scope. In timeline.yaml, every time period can set its own analysis mode independently — for example, incremental analysis in the morning and a full-day summary in the evening.

Mode	Analysis scope	Best for
Mode	Analysis scope	Best for
`follow_report`	Follows the current push content	Automatically follows the value of report.mode. For example, when report.mode=daily the AI analyzes the full day's data; when report.mode=incremental it only analyzes new content
`daily`	The full day's data	Great for an evening recap of the whole day's trending topics
`current`	A snapshot of the current rankings	Analyzes what is hot across platforms right now
`incremental`	New entries only	Analyzes only what is new since the last push

# Set a different analysis mode per time period in timeline.yaml
periods:
  morning:
    start: "08:00"
    end: "10:00"
    analysis: incremental    # morning: analyze new content only

  evening:
    start: "19:00"
    end: "21:00"
    analysis: daily           # evening: recap the whole day's trends

Customizing the analysis prompt

You can adjust the style and angle of the AI analysis by editing the prompt file. Edit config/ai_analysis_prompt.txt to customize the AI's persona and analysis style.

Tips for editing the prompt

Prompt file format

Debug mode

If the analysis results don't match your expectations, set advanced.debug: true in config.yaml to enable debug mode. This lets you see the full prompt sent to the AI and the raw response, making it easier to troubleshoot.

Cost note

AI analysis consumes API usage quota. With the DeepSeek model, a single analysis usually costs less than 0.01 CNY. If you're cost-sensitive, you can keep spending in check by reducing the analysis frequency (for example, enabling it only for the evening summary).