iMessage

# This uses some example data
import requests


def download_drive_file(url: str, output_path: str = "chat.db") -> None:
    file_id = url.split("/")[-2]
    download_url = f"https://drive.google.com/uc?export=download&id={file_id}"

    response = requests.get(download_url)
    if response.status_code != 200:
        print("Failed to download the file.")
        return

    with open(output_path, "wb") as file:
        file.write(response.content)
        print(f"File {output_path} downloaded.")


url = (
    "https://drive.google.com/file/d/1NebNKqTA2NXApCmeH6mu0unJD2tANZzo/view?usp=sharing"
)

# Download file to chat.db
download_drive_file(url)

from langchain_community.chat_loaders.imessage import IMessageChatLoader

loader = IMessageChatLoader(
    path="./chat.db",
)

from typing import List

from langchain_community.chat_loaders.utils import (
    map_ai_messages,
    merge_chat_runs,
)
from langchain_core.chat_sessions import ChatSession

raw_messages = loader.lazy_load()
# Merge consecutive messages from the same sender into a single message
merged_messages = merge_chat_runs(raw_messages)
# Convert messages from "Tortoise" to AI messages. Do you have a guess who these conversations are between?
chat_sessions: List[ChatSession] = list(
    map_ai_messages(merged_messages, sender="Tortoise")
)

# Now all of the Tortoise's messages will take the AI message class
# which maps to the 'assistant' role in OpenAI's training format
chat_sessions[0]["messages"][:3]

from langchain_community.adapters.openai import convert_messages_for_finetuning

training_data = convert_messages_for_finetuning(chat_sessions)
print(f"Prepared {len(training_data)} dialogues for training")

%pip install --upgrade --quiet  langchain-openai

import json
import time
from io import BytesIO

import openai

# We will write the jsonl file in memory
my_file = BytesIO()
for m in training_data:
    my_file.write((json.dumps({"messages": m}) + "\n").encode("utf-8"))

my_file.seek(0)
training_file = openai.files.create(file=my_file, purpose="fine-tune")

# OpenAI audits each training file for compliance reasons.
# This make take a few minutes
status = openai.files.retrieve(training_file.id).status
start_time = time.time()
while status != "processed":
    print(f"Status=[{status}]... {time.time() - start_time:.2f}s", end="\r", flush=True)
    time.sleep(5)
    status = openai.files.retrieve(training_file.id).status
print(f"File {training_file.id} ready after {time.time() - start_time:.2f} seconds.")

job = openai.fine_tuning.jobs.create(
    training_file=training_file.id,
    model="gpt-3.5-turbo",
)

status = openai.fine_tuning.jobs.retrieve(job.id).status
start_time = time.time()
while status != "succeeded":
    print(f"Status=[{status}]... {time.time() - start_time:.2f}s", end="\r", flush=True)
    time.sleep(5)
    job = openai.fine_tuning.jobs.retrieve(job.id)
    status = job.status

print(job.fine_tuned_model)

from langchain_openai import ChatOpenAI

model = ChatOpenAI(
    model=job.fine_tuned_model,
    temperature=1,
)

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are speaking to hare."),
        ("human", "{input}"),
    ]
)

chain = prompt | model | StrOutputParser()

for tok in chain.stream({"input": "What's the golden thread?"}):
    print(tok, end="", flush=True)