sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

change llm model and slight prompt adjustment

Browse source
This commit is contained in:
sirius0xdev 2026-02-11 04:42:44 +00:00
parent f126d9cacb
commit 05de0e24a3
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
apps/base/customer1/news_bot/analyst-cronjob.yaml
View file

@ -22,7 +22,7 @@ spec:
- name: ollama-storage
mountPath: /root/.ollama
command: ["/bin/sh", "-c"]
args: ["ollama serve & sleep 5 && ollama pull qwen2.5:14b-instruct"]
args: ["ollama serve & sleep 5 && ollama pull qwen2.5:32b-instruct"]
- name: ollama-sidecar

6
apps/base/customer1/news_bot/gemma-configmap.yaml
View file

@ -9,10 +9,10 @@ data:
DB_USER: "news_app"
DB_PORT: "5432"
LLM_URL: "http://localhost:11434"
MODEL_NAME: "qwen2.5:14b-instruct"
MODEL_NAME: "qwen2.5:32b-instruct"
SUMMARY_PROMPT: |
SUMMARY_PROMPT: |
You are Sirius Media Trading Brief — a fast, Telegram-optimized news & trading insight generator.
You are Sirius Media a fast, Telegram-optimized news & trading insight generator.
Your ONLY source of information is the FINAL INPUT DATA below.
You MUST NOT use any prior training data, external knowledge, recalled events, or assumptions.
@ -29,7 +29,7 @@ data:
• For weather-related news (storms, droughts, floods, hurricanes, freezes, heatwaves, etc.), always note potential effects on futures (corn, wheat, soy, coffee, natural gas, crude oil, etc.).
• Identify 3–6 most impactful developments. For each: 4–6 sentences covering key facts, context, potential market consequences, and strategic/trading relevance.
• List 4–7 unusual or standout stories (3–4 sentences each).
• At the end, give 4–8 trade ideas (stocks, futures contracts, forex pairs) that could be influenced by the news.
• At the end, give 4–8 trade ideas (stocks, futures contracts, forex pairs) that could be influenced by the news. This is the only time past training data can be used.
- Format: Ticker / Symbol – Direction (Long/Short/Neutral) – Rationale (1–2 sentences) – Risk level (Low/Med/High)
- Use real tickers/symbols only if clearly inferable from the data (e.g. company names mentioned).
• Keep total output 600–1100 words. Be concise yet insightful.