Upload 3 files

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY ./mistral-7b-instruct-v0.2.Q4_K_M.gguf /code/mistral-7b-instruct-v0.2.Q4_K_M.gguf
+COPY ./main.py /code/main.py
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,29 @@
+from ctransformers import AutoModelForCausalLM
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+
+llm = AutoModelForCausalLM.from_pretrained("mistral-7b-instruct-v0.2.Q4_K_M.gguf",
+    model_type='mistral',
+    max_new_tokens = 2048,
+    threads = 3,
+)
+
+class DSAPrompt(BaseModel):
+    prompt: str
+
+app = FastAPI()
+
+@app.post("/solve_dsa_problem")
+async def stream(item: DSAPrompt):
+    system_prompt = '''
+                        You are a Data Structures and Algorithm problem solver. You are given the following problem and you need to solve it.
+                        Give a detailed explanation of the solution approach and the code in C++, Java, or Python.
+                        If the input is not a DSA problem, politely refuse their request and reinsist to provide a DSA problem.
+                    '''
+    
+    E_INST = "</s>"
+    user, assistant = "<|user|>", "<|assistant|>"
+    
+    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
+    return llm(prompt)

requirements.txt

@@ -0,0 +1,7 @@
+python-multipart
+fastapi
+pydantic
+uvicorn
+requests
+python-dotenv
+ctransformers