first attempt at transformer pipeline llm endpoint

main.py

@@ -1,7 +1,16 @@
+from transformers import pipeline
 from fastapi import FastAPI
+from payload import SomeText
 
 app = FastAPI()
 
-@app.get("/")
-def read_root():
-    return {"Hello": "World!"}
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
+
+@app.get("/api/check-heartbeat")
+def get_heartbeat():
+    return {"Status": "Running. Try out the endpoints in swagger"}
+
+@app.post("/api/generate", summary="Generate text from prompt", tags=["Generate"], response_model=SomeText)
+def inference(input_prompt: SomeText):
+    output = pipe_flan(input_prompt)
+    return {"output": output[0]["generated_text"]}

payload.py

@@ -12,4 +12,6 @@ class SomeText(BaseModel):
                 }
             ]
         }
-    }
+    }
+
+

requirements.txt

@@ -1,6 +1,5 @@
-fastapi==0.74.*
-requests==2.27.*
-sentencepiece==0.1.*
 torch==1.11.*
 transformers==4.*
 uvicorn[standard]==0.17.*
+fastapi==0.99.1
+pydantic==1.10.12