diff --git a/apps/base/customer1/news_bot/analyst-cronjob.yaml b/apps/base/customer1/news_bot/analyst-cronjob.yaml index 87d4d85..fc67cc6 100644 --- a/apps/base/customer1/news_bot/analyst-cronjob.yaml +++ b/apps/base/customer1/news_bot/analyst-cronjob.yaml @@ -9,38 +9,6 @@ spec: spec: template: spec: - volumes: - - name: ollama-storage - persistentVolumeClaim: - claimName: ollama-storage - - - initContainers: - - name: model-puller - image: ollama/ollama:latest - volumeMounts: - - name: ollama-storage - mountPath: /root/.ollama - command: ["/bin/sh", "-c"] - args: ["ollama serve & sleep 5 && ollama pull mistral-small"] - - - - name: ollama-sidecar - image: ollama/ollama:latest - restartPolicy: Always - env: - - name: OLLAMA_DEBUG - value: "2" - - name: OLLAMA_LOG_LEVEL - value: "DEBUG" - ports: - - containerPort: 11434 - volumeMounts: - - name: ollama-storage - mountPath: /root/.ollama - resources: - limits: - nvidia.com/gpu: 1 containers: - name: analyst image: siriussec/summarizerlocal:3.5 @@ -57,4 +25,3 @@ spec: restartPolicy: OnFailure - diff --git a/apps/base/customer1/news_bot/configmap.yaml b/apps/base/customer1/news_bot/configmap.yaml index cc8673b..6485cdc 100644 --- a/apps/base/customer1/news_bot/configmap.yaml +++ b/apps/base/customer1/news_bot/configmap.yaml @@ -8,8 +8,9 @@ data: DB_NAME: "news_app_db" DB_USER: "news_app" DB_PORT: "5432" - LLM_URL: "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent" - MODEL_NAME: "" + LLM_BASE_URL: "http://rtx6000-brain-service.customer1.svc.cluster.local:8000/v1" + MODEL_NAME: "edp1096/Huihui-Qwen3.6-27B-abliterated-FP8" + LLM_API_KEY: "sk-dummy" SUMMARY_PROMPT: | You are an expert news analyst working for DARPA. Your task is to deliver thorough, insightful analysis of the provided news articles. diff --git a/apps/base/customer1/news_bot/deepseek-configmap.yaml b/apps/base/customer1/news_bot/deepseek-configmap.yaml index 2f28a1e..c3d45c7 100644 --- a/apps/base/customer1/news_bot/deepseek-configmap.yaml +++ b/apps/base/customer1/news_bot/deepseek-configmap.yaml @@ -8,8 +8,9 @@ data: DB_NAME: "news_app_db" DB_USER: "news_app" DB_PORT: "5432" - LLM_BASE_URL: "http://a100-brain-vllm:8000/v1" - MODEL_NAME: "deepseek-r1:70b" + LLM_BASE_URL: "http://rtx6000-brain-service.customer1.svc.cluster.local:8000/v1" + MODEL_NAME: "edp1096/Huihui-Qwen3.6-27B-abliterated-FP8" + LLM_API_KEY: "sk-dummy" MAP_PROMPT: | @@ -21,8 +22,7 @@ data: Translate every non-English article into flawless, natural English. Compress the batch into dense, structured, machine-readable summaries that preserve every tradable signal while slashing token count. - # REASONING PROTOCOL (MANDATORY PHASE — FULL ACTIVATION) - + # REASONING PROTOCOL (MANDATORY THINKING PHASE — FULL ACTIVATION) Execute the following 9-step protocol for the whole batch. Show every step internally before producing the final output. 1. PER-ARTICLE DECONSTRUCTION @@ -43,7 +43,6 @@ data: - Ensure every bullet is dense, factual, and zero-fluff. 9. BATCH-LEVEL SUMMARY - Identify the 2-3 strongest overarching signals in the entire batch. - # TASK For EVERY article in the batch, output the exact block below. @@ -78,13 +77,12 @@ data: SUMMARY_PROMPT: | # ROLE - Lead Futures Strategist & Macro-Economist with Elite Reasoning + Technical Integration Engine (DeepSeek-R1 mode). + Lead Futures Strategist & Macro-Economist with Elite Reasoning + Technical Integration Engine. # OBJECTIVE Synthesize the news batch + all supplied price/volume data into a high-conviction "Trading Edge" report. Extract precise, actionable trade setups with exact entry triggers, layered price targets, TP levels, and SL placements. Use the technical data to anchor every level in current market structure. - # REASONING PROTOCOL (MANDATORY PHASE — FULL ACTIVATION) - + # REASONING PROTOCOL (MANDATORY THINKING PHASE — FULL ACTIVATION) Execute the following 10-step protocol in sequence. Show every logical step before outputting the final report. 1. ARTICLE DECONSTRUCTION → Core facts, symbols impacted, time horizon, credibility. @@ -113,7 +111,6 @@ data: - Rank only the top 5-7 highest-edge setups by (conviction × magnitude × R:R). 10. FINAL CONVCTION CHECK - Overall report conviction after critique. - TASK Produce only high-signal, fully actionable futures setups. Every level must be justified by either: @@ -145,7 +142,7 @@ data: CONSTRAINTS - Every price level, TP, and SL must be traceable to the supplied price/volume data or explicit news+history. - - No vague language. No “around here” or “watch this area.” + - No vague language. No "around here" or "watch this area." - Use exact futures notation (/CL, /NG, /ES, /NQ, /GC, /SI, /HG, etc.). - Keep bullets dense but scannable (Telegram-ready). - Zero hype. If evidence is marginal, state confidence honestly. diff --git a/apps/base/customer1/news_bot/deepseek-summarizer.yaml b/apps/base/customer1/news_bot/deepseek-summarizer.yaml index d85d4af..2956802 100644 --- a/apps/base/customer1/news_bot/deepseek-summarizer.yaml +++ b/apps/base/customer1/news_bot/deepseek-summarizer.yaml @@ -10,59 +10,6 @@ spec: spec: template: spec: - nodeSelector: - accelerator: "a100-80gb" - - # 2. ACCEPT THE GPU TAINT - tolerations: - - key: "nvidia.com/gpu-a100-80gb" - operator: "Equal" - value: "present" - effect: "NoSchedule" - # Standard GPU toleration for GKE system - - key: "nvidia.com/gpu" - operator: "Exists" - effect: "NoSchedule" - - volumes: - - name: deepseek-storage - persistentVolumeClaim: - claimName: deepseek-storage - - - initContainers: - - name: model-puller - image: ollama/ollama:latest - volumeMounts: - - name: deepseek-storage - mountPath: /root/.ollama - command: ["/bin/sh", "-c"] - args: ["ollama serve & sleep 5 && ollama pull deepseek-r1:70b"] - - - - name: ollama-sidecar - image: ollama/ollama:latest - restartPolicy: Always - env: - - name: OLLAMA_DEBUG - value: "2" - - name: OLLAMA_LOG_LEVEL - value: "DEBUG" - ports: - - containerPort: 11434 - volumeMounts: - - name: deepseek-storage - mountPath: /root/.ollama - - resources: - limits: - nvidia.com/gpu: "1" - memory: "90Gi" - requests: - nvidia.com/gpu: "1" - memory: "80Gi" - cpu: "4" - containers: - name: analyst image: siriussec/summarizerlocal:3.6 diff --git a/apps/base/customer1/news_bot/gemma-configmap.yaml b/apps/base/customer1/news_bot/gemma-configmap.yaml index dba9fd7..aadf519 100644 --- a/apps/base/customer1/news_bot/gemma-configmap.yaml +++ b/apps/base/customer1/news_bot/gemma-configmap.yaml @@ -8,9 +8,10 @@ data: DB_NAME: "news_app_db" DB_USER: "news_app" DB_PORT: "5432" - LLM_BASE_URL: "http://a100-brain-vllm:8000/v1" - MODEL_NAME: "mistral-small" - + LLM_BASE_URL: "http://rtx6000-brain-service.customer1.svc.cluster.local:8000/v1" + MODEL_NAME: "edp1096/Huihui-Qwen3.6-27B-abliterated-FP8" + LLM_API_KEY: "sk-dummy" + MAP_PROMPT: | You are a state of the art AI News analysis diff --git a/apps/base/customer1/news_bot/kustomization.yaml b/apps/base/customer1/news_bot/kustomization.yaml index 1bab5dd..8066cda 100644 --- a/apps/base/customer1/news_bot/kustomization.yaml +++ b/apps/base/customer1/news_bot/kustomization.yaml @@ -4,18 +4,15 @@ kind: Kustomization namespace: customer1 resources: - configmap.yaml - - gemini-apikey.yaml - scraper-cronjob.yaml - scrapy-urls-configmap.yaml - scrapy-configmap.yaml - telebot-cronjob.yaml - telebot-secret.yaml -# - gemma-configmap.yaml - # - analyst-cronjob.yaml - - ollama-storage.yaml + - gemma-configmap.yaml + - analyst-cronjob.yaml - news-app-password.yaml - news-app-db.yaml - #- deepseek-summarizer.yaml - deepseek-configmap.yaml - - deepseek-storage.yaml - #- new_deepseek.yaml + - deepseek-summarizer.yaml + #- new_deepseek.yaml diff --git a/apps/base/customer1/news_bot/new_deepseek.yaml b/apps/base/customer1/news_bot/new_deepseek.yaml index 1b12e67..d1e3bf9 100644 --- a/apps/base/customer1/news_bot/new_deepseek.yaml +++ b/apps/base/customer1/news_bot/new_deepseek.yaml @@ -11,59 +11,6 @@ spec: spec: template: spec: - nodeSelector: - accelerator: "a100-80gb" - - # 2. ACCEPT THE GPU TAINT - tolerations: - - key: "nvidia.com/gpu-a100-80gb" - operator: "Equal" - value: "present" - effect: "NoSchedule" - # Standard GPU toleration for GKE system - - key: "nvidia.com/gpu" - operator: "Exists" - effect: "NoSchedule" - - volumes: - - name: deepseek-storage - persistentVolumeClaim: - claimName: deepseek-storage - - - initContainers: - - name: model-puller - image: ollama/ollama:latest - volumeMounts: - - name: deepseek-storage - mountPath: /root/.ollama - command: ["/bin/sh", "-c"] - args: ["ollama serve & sleep 5 && ollama pull deepseek-r1:70b"] - - - - name: ollama-sidecar - image: ollama/ollama:latest - restartPolicy: Always - env: - - name: OLLAMA_DEBUG - value: "2" - - name: OLLAMA_LOG_LEVEL - value: "DEBUG" - ports: - - containerPort: 11434 - volumeMounts: - - name: deepseek-storage - mountPath: /root/.ollama - - resources: - limits: - nvidia.com/gpu: "1" - memory: "90Gi" - requests: - nvidia.com/gpu: "1" - memory: "80Gi" - cpu: "4" - containers: - name: analyst image: siriussec/summarizerlocal:3.8