afspiegeling/rewards-farmer
1
0
Fork 0
mirror of https://github.com/User0332/rewards-farmer.git synced 2026-09-16 01:31:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

add a query source that does not need a language model

Browse Source 
Idea taken from TheNetsky/Microsoft-Rewards-Script, which builds search terms
from public feeds rather than a model. No code from it: that project is
GPL-3.0 and this one is MIT, so only the approach crosses over.

The LLM has exactly two call sites here, both producing a short string to type
into Bing. Everything the dependency costs, an Ollama account, cloud usage and
the provider work in #15, is paid for search strings. Three keyless sources
answer the same question:

  Google Trends RSS    queries people are actually typing right now
  Wikipedia most-read  topic seeds when trends is unavailable
  Bing autosuggest     expands a seed into related queries

Autosuggest is what makes the chaining work. Asking Bing what follows a term
returns queries Bing already expects, which is nearer to what the prompt in
llm_utils was reaching for than a model guessing unaided.

Selected with QUERY_SOURCE=trends. The default stays llm, so no existing setup
changes. stdlib only, no new dependencies.

Measured against the LLM on the same cards from a live account:

  card                     llm                                    trends
  airport parking          best rates airport parking reservations reserve airport parking best rates
  checking vs savings      compare checking vs savings accounts    compare checking savings account options
  cruise deals             best cruise deals and destinations      cruise deals destinations

Verified live with OLLAMA_HOST pointed at a dead port, so nothing could reach
a model: five queries generated from feeds and three typed into Bing, each
landing on a real results page.

Every source degrades to an empty list rather than raising, and both entry
points fall back, to the trimmed task description and to nouns.txt. A search
that does not happen costs points; a run that dies costs the rest of the day.
This commit is contained in:
Ethan Stoner
2026-08-26 15:05:09 -07:00
parent 6f6ffa3fa4
commit af03afcc6d
4 changed files with 281 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+16
View File
@@ -19,6 +19,22 @@ cd rewards-farmer
# Edit the included nouns.txt file to add or replace words as needed
```
# Where search queries come from
The bot needs short strings to type into Bing. Two backends produce them, set with `QUERY_SOURCE`:
| `QUERY_SOURCE` | Needs | Notes |
| --- | --- | --- |
| `llm` (default) | Ollama account + model | Current behaviour, unchanged |
| `trends` | nothing | Google Trends, Wikipedia and Bing autosuggest |
```sh
QUERY_SOURCE=trends python src/main.py # bash
$env:QUERY_SOURCE="trends"; python src/main.py # PowerShell
```
`trends` needs no account, no API key and no model download, so the Ollama setup below is optional if you use it. If every feed is unreachable it falls back to `nouns.txt` rather than failing the run.
You should also have an Ollama account created (for the LLM), the `ollama` tool installed, and you should have signed in to the Ollama CLI via the command line using `ollama signin`. This project will use a minimal amount of Ollama cloud usage using `gemma4:cloud`. If you wish to use a different model, please change the `model` parameter in the `get_ollama_response` function in `src/llm_utils.py`.
You must also provide an image for the script to upload to complete the visual search task. Currently, this image is named `keypress_times.png` and is located in the root directory of the project (yes, I used a random image from my keyboard analysis to do this). You may provide an image of your own, just ensure that the absolute path of the image is placed in the `VISUAL_SEARCH_IMAGE_PATH` constant at the top of `rewards_tasks.py`.