Upload 6 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 src/data/documents/Recon[[:space:]]Robot[[:space:]]Thrusters.pdf filter=lfs diff=lfs merge=lfs -text
+data/documents/Recon[[:space:]]Robot[[:space:]]Thrusters.pdf filter=lfs diff=lfs merge=lfs -text

config/model_config.yaml

@@ -0,0 +1,17 @@
+model:
+  language_name: qwen2.5:7b
+  embedding: bge-m3
+  predictive_model: model/predictive_model_RandomForest.pkl
+  xia_model: model/xia_config.pkl
+
+chunk:
+  size: 512
+  overlap: 64
+
+url:
+  server: http://api:8080/
+
+documents:
+  breakpoints: ./data/documents/
+
+storage: ./storage/

data/documents/Recon Robot Thrusters.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33c6d9cf7e676684d9de4920057aa5a4337e902555c1ed5bcbecb4aea44c4008
+size 349080

model/predictive_model_RandomForest.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199ac096cc7f21f2a9abe6493f57c1a32c580fa29e6da8563a48b44e718e75a3
+size 74705553

model/xia_config.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f55ebd665920196c2c31201eeaa0e3a8bb04a6c46eb4a836d0a69ffb6997241
+size 4097281

server.py

@@ -0,0 +1,72 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from typing import List
+from src.predictive.custom_model import ModelAPI
+from src.slm.core import configure_llm
+from src.slm.operation import workflow
+from src.slm.query import xia_query, summary_query
+from src.slm.retrieval import Retrieval
+
+modelAPI = ModelAPI()
+configure_llm()
+agent = workflow()
+retrieval = Retrieval()
+
+app = FastAPI(title="Recon Robot Health Agent", description="Recon Robot Health Agent API")
+
+class SensorInput(BaseModel):
+    instances: List[float]
+
+class QueryInput(BaseModel):
+    query: str
+
+def alert_message(status):
+  return f"The status of the thruster is {status}"
+
+async def identify_root_cause(agent, thruster_data):
+  sensor_data = [{**thruster_data}]
+  factor_query = xia_query(sensor_data[0])
+  sum_query = summary_query()
+  return await agent.run(user_msg=f"{factor_query} {sum_query}")
+
+async def search_document(retrieval, text):
+  return await retrieval.query_context(text)
+
+
+@app.post("/predict")
+def predict(data: SensorInput):
+    features = {
+        'voltage': data.instances[0],
+        'current': data.instances[1],
+        'power': data.instances[2],
+        'temperature': data.instances[3],
+        'driver_temperature': data.instances[4],
+        'speed_rpm': data.instances[5],
+        'thruster_id_encoded': data.instances[6]
+        }
+    prediction = modelAPI.predict(features)
+    status = alert_message(prediction)
+
+    return {"prediction": status}
+
+
+@app.post("/rca")
+async def rca(data: SensorInput):
+    features = {
+        'voltage': data.instances[0],
+        'current': data.instances[1],
+        'power': data.instances[2],
+        'temperature': data.instances[3],
+        'driver_temperature': data.instances[4],
+        'speed_rpm': data.instances[5],
+        'thruster_id_encoded': data.instances[6]
+        }
+    long_response = await identify_root_cause(agent,  features)
+
+    return {"rca": str(long_response)}
+
+
+@app.post('/semantic')
+async def semantic(data: QueryInput):
+  response =  await search_document(retrieval, data.query)
+  return {'search': str(response)}