Upload files

app.py

@@ -0,0 +1,97 @@
+import numpy as np
+import pandas as pd
+import openai
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores.faiss import FAISS
+from langchain.docstore.document import Document
+from langchain.prompts import PromptTemplate
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import gradio as gr
+import os
+import PyPDF2
+import zipfile
+
+openai.api_key = "sk-"+os.environ['OPENAI_API_KEY']
+embeddings = OpenAIEmbeddings()
+
+df = pd.read_csv('reglamento-cdmx.csv')
+text = df['text'].tolist()
+
+text_splitter = RecursiveCharacterTextSplitter(
+    # Set a really small chunk size, just to show.
+    chunk_size=500,
+    chunk_overlap=0,
+    length_function=len,
+)
+
+texts = text_splitter.split_text(text)
+
+docsearch = FAISS.from_texts(texts, embeddings)
+
+
+def proper_query(query):
+    prompt = f"El siguiente texto es una pregunta en español: {query}\n\n¿Cómo debería ser la pregunta para que sea correcta en español?\nPregunta corregida:"
+    response = openai.Completion.create(
+        engine="text-davinci-003", prompt=prompt, max_tokens=1000, temperature=0.2)
+    return response.choices[0].text
+
+
+def answer_question(query):
+    query = proper_query(query)
+    docs = docsearch.similarity_search(query)
+    refine_prompt_template = (
+        "The original question is as follows: {question}\n"
+        "We have provided an existing answer: {existing_answer}\n"
+        "You have the opportunity to refine the existing answer,"
+        "only if needed, with the context below.\n"
+        "------------\n"
+        "{context_str}\n"
+        "------------\n"
+        "If that context is not helpful to answer the question, then omit it.\n"
+        "Your answer should be correct, and concise.\n"
+        "Shorten the answer if possible.\n"
+        "Reply in the same language as the question.\n"
+        "Answer:"
+    )
+    refine_prompt = PromptTemplate(
+        input_variables=["question", "existing_answer", "context_str"],
+        template=refine_prompt_template,
+    )
+
+    initial_qa_template = (
+        "Context information is below. \n"
+        "---------------------\n"
+        "{context_str}"
+        "\n---------------------\n"
+        "Given the context information and not prior knowledge, "
+        "answer the question: {question}\n"
+    )
+    initial_qa_prompt = PromptTemplate(
+        input_variables=["context_str", "question"], template=initial_qa_template
+    )
+    chain = load_qa_chain(OpenAI(temperature=0), chain_type="refine", return_refine_steps=False,
+                          question_prompt=initial_qa_prompt, refine_prompt=refine_prompt)
+    answer = chain({"input_documents": docs, "question": query},
+                   return_only_outputs=True)['output_text']
+    return answer
+
+
+demo = gr.Interface(
+    fn=answer_question,
+    inputs=[
+        gr.Textbox(label="Hola, ¿cuál es tu pregunta?", lines=3,),
+    ],
+    outputs=[gr.Textbox(label="Respuesta: ")],
+    title="Asesor de Reglamento de Tránsito CDMX",
+    examples=[
+        ["me pueden detener por no llevar casco?"],
+        ["qué pasa si no tengo licencia de conducir?"],
+        ["qué pasa si no tengo placas?"],
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+openai==0.25.0
+PyPDF2==3.0.1
+langchain==0.0.68
+zipfile36==0.1.3