Upload 4 files

Dockerfile

@@ -0,0 +1,25 @@
+# For more information, please refer to https://aka.ms/vscode-docker-python
+FROM python:3.10-slim
+
+EXPOSE 8000
+
+# Keeps Python from generating .pyc files in the container
+ENV PYTHONDONTWRITEBYTECODE=1
+
+# Turns off buffering for easier container logging
+ENV PYTHONUNBUFFERED=1
+
+# Install pip requirements
+COPY requirements.txt .
+RUN python -m pip install -r requirements.txt
+
+WORKDIR /app
+COPY . /app
+
+# Creates a non-root user with an explicit UID and adds permission to access the /app folder
+# For more info, please refer to https://aka.ms/vscode-docker-python-configure-containers
+RUN adduser -u 5678 --disabled-password --gecos "" appuser && chown -R appuser /app
+USER appuser
+
+# During debugging, this entry point will be overridden. For more information, please refer to https://aka.ms/vscode-docker-python-debug
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "-k", "uvicorn.workers.UvicornWorker", "app:app"]

app.py

@@ -0,0 +1,32 @@
+
+import json
+import module_q 
+import datetime
+from fastapi import FastAPI
+from typing import Union
+from fastapi.responses import FileResponse
+from fastapi import APIRouter
+
+
+app = FastAPI()
+favicon_path = 'favicon.ico'
+
+
+
+@app.get("/")
+def read_root():
+    return {"query": "/query/your_query"}
+
+
+@app.get("/query/{ask}")
+def read_query( ask: Union[str, None]):
+    now = datetime.datetime.now()
+    print("Request time :",now)
+    res=module_q.search_query_data(ask)
+    now = datetime.datetime.now()
+    print("Response time :",now)
+    print("res :",res)
+    return res
+
+
+ 

module_q.py

@@ -0,0 +1,88 @@
+from pathlib import Path
+from typing import List, Tuple
+from langchain import PromptTemplate, LLMChain
+from langchain.document_loaders import TextLoader
+from langchain.embeddings import LlamaCppEmbeddings
+from langchain.llms import GPT4All
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores.faiss import FAISS
+from pydantic import BaseModel, Field
+from langchain.chains import ConversationalRetrievalChain
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.llms import LlamaCpp
+import os.path
+
+
+import langchain
+from langchain.cache import InMemoryCache
+langchain.llm_cache = InMemoryCache()
+
+# Constants
+local_path = "./models/gpt4all-converted.bin" #GPT4 module 1
+#local_path = "./models/ggml-gpt4all-l13b-snoozy.bin"
+
+
+model_path = "./models/ggml-model-q4_0.bin" #1st Embeddings
+#model_path = './models/ggjt-model.bin'  #2st Embedding
+text_path = "./docs/acapglobal.txt"
+index_path = "./acapglobal_index"
+
+
+# Functions
+def initialize_embeddings() -> LlamaCppEmbeddings:
+    return LlamaCppEmbeddings(model_path=model_path)
+    
+def load_documents() -> List:
+    loader = TextLoader(text_path,encoding="utf-8")
+    return loader.load()
+
+def split_chunks(sources: List) -> List:
+    chunks = []
+    splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=32)
+    for chunk in splitter.split_documents(sources):
+        chunks.append(chunk)
+    return chunks
+
+def generate_index(chunks: List, embeddings: LlamaCppEmbeddings) -> FAISS:
+    texts = [doc.page_content for doc in chunks]
+    metadatas = [doc.metadata for doc in chunks]
+    return FAISS.from_texts(texts, embeddings, metadatas=metadatas)
+
+
+# Main execution
+llm = GPT4All(model=local_path, n_ctx=512, verbose=True,cache=True,embedding=True)
+print('llm GPT4All set.')
+embeddings = initialize_embeddings()
+
+
+# when refresh document
+#
+
+# print('initialize_embeddings.')
+# sources = load_documents()
+# print('load_documents.')
+# chunks = split_chunks(sources)
+# print('split_chunks')
+# vectorstore = generate_index(chunks, embeddings)
+# print('generate_index')
+# vectorstore.save_local("acapglobal_index")
+# print('vectorstore: save_local')
+
+#
+# End When refresh document
+
+
+chat_history = []
+#index = FAISS.load_local(index_path, embeddings)
+index = FAISS.load_local(index_path, embeddings)
+
+qa = ConversationalRetrievalChain.from_llm(llm, index.as_retriever(), max_tokens_limit=400)
+
+def search_query_data(s_query):
+    print("search_query:")
+    print( s_query)
+    retrieval=qa({"question": s_query, "chat_history": chat_history})
+    return retrieval
+
+
+

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.74.*
+requests==2.27.*
+uvicorn[standard]==0.17.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers==4.*