Upload 3 files

Dockerfile

@@ -0,0 +1,26 @@
+FROM python:3.7
+
+WORKDIR /code
+
+COPY requirements-fastapi.txt ./
+
+# Installing libGL
+RUN apt-get update && apt-get install -y \
+    libgl1-mesa-dev
+
+RUN apt-get install -y poppler-utils libpoppler-cpp-dev
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements-fastapi.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app/
+
+CMD ["uvicorn", "endpoints:app", "--host", "0.0.0.0", "--port", "7860"]

endpoints.py

@@ -0,0 +1,80 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+import os
+import requests
+# from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+
+key = os.environ.get("huggingface_key")
+openai_api_key = os.environ.get("openai_key")
+app = FastAPI(openapi_url="/api/v1/sparrow-data/openapi.json", docs_url="/api/v1/sparrow-data/docs")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+    allow_credentials=True,
+)
+API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-v0.1"
+headers = {"Authorization": f"Bearer {key}"}
+
+def query(payload):
+	response = requests.post(API_URL, headers=headers, json=payload)
+	return response.json()
+
+
+
+
+
+
+
+tokenizer = AutoTokenizer.from_pretrained("WizardLM/WizardCoder-1B-V1.0")
+base_model = AutoModelForCausalLM.from_pretrained("WizardLM/WizardCoder-1B-V1.0")
+
+pipe = pipeline("text-generation",
+                model=base_model,
+                tokenizer=tokenizer,
+                max_length=4000,
+                do_sample=True,
+                top_p=0.95,
+                repetition_penalty=1.2,
+               )
+# hf_llm = HuggingFacePipeline(pipeline=pipe)
+
+
+@app.get("/")
+def root():
+    return {"message": "R&D LLM API"}
+@app.get("/get")
+def get():
+    result = pipe("name 5 programming languages",do_sample=False)
+    print(result)
+    return {"message": result}
+
+
+async def askLLM(prompt):
+    output = pipe(prompt,do_sample=False)
+    return output
+
+@app.post("/ask_llm")
+async def ask_llm_endpoint(prompt: str):
+    # result = await askLLM(prompt)
+    result = pipe(prompt,do_sample=False)
+    return {"result": result}
+
+
+@app.post("/ask_HFAPI")
+def ask_HFAPI_endpoint(prompt: str):
+    result = query(prompt)
+    return {"result": result}
+    
+from langchain.llms import OpenAI
+
+llm = OpenAI(model_name="text-davinci-003", temperature=0.5, openai_api_key=openai_api_key)
+
+@app.post("/ask_GPT")
+def ask_GPT_endpoint(prompt: str):
+    result = llm(prompt)
+    return {"result": result}

requirements-fastapi.txt

@@ -0,0 +1,15 @@
+python-poppler==0.4.1
+fastapi==0.96.0
+python-multipart
+motor==3.1.2
+pydantic==1.10.8
+pycryptodome==3.18.0
+uvicorn[standard]
+langchain
+transformers
+torch
+requests
+openai==0.27.8
+sentencepiece==0.1.99
+accelerate==0.19.0
+bitsandbytes==0.39.0