Facebook Messenger

# This uses some example data
import zipfile

import requests


def download_and_unzip(url: str, output_path: str = "file.zip") -> 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.")

    with zipfile.ZipFile(output_path, "r") as zip_ref:
        zip_ref.extractall()
        print(f"File {output_path} has been unzipped.")


# URL of the file to download
url = (
    "https://drive.google.com/file/d/1rh1s1o2i7B-Sk1v9o8KNgivLVGwJ-osV/view?usp=sharing"
)

# Download and unzip
download_and_unzip(url)

directory_path = "./hogwarts"

from langchain_community.chat_loaders.facebook_messenger import (
    FolderFacebookMessengerChatLoader,
    SingleFileFacebookMessengerChatLoader,
)

loader = SingleFileFacebookMessengerChatLoader(
    path="./hogwarts/inbox/HermioneGranger/messages_Hermione_Granger.json",
)

chat_session = loader.load()[0]
chat_session["messages"][:3]

loader = FolderFacebookMessengerChatLoader(
    path="./hogwarts",
)

chat_sessions = loader.load()
len(chat_sessions)

from langchain_community.chat_loaders.utils import (
    map_ai_messages,
    merge_chat_runs,
)

merged_sessions = merge_chat_runs(chat_sessions)
alternating_sessions = list(map_ai_messages(merged_sessions, "Harry Potter"))

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

from langchain_community.adapters.openai import convert_messages_for_finetuning

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

training_data[0][:3]

# Our chat is alternating, we will make each datapoint a group of 8 messages,
# with 2 messages overlapping
chunk_size = 8
overlap = 2

training_examples = [
    conversation_messages[i : i + chunk_size]
    for conversation_messages in training_data
    for i in range(0, len(conversation_messages) - chunk_size + 1, chunk_size - overlap)
]

len(training_examples)

%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_examples:
    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(
    [
        ("human", "{input}"),
    ]
)

chain = prompt | model | StrOutputParser()

for tok in chain.stream({"input": "What classes are you taking?"}):
    print(tok, end="", flush=True)