Running Llama 3, Mixtral, and GPT-4o

# Separate all the context together by space, reverse order.
# See “Lost in the middle” arxiv.org paper.
contexts_combined = ' '.join(reversed(contexts))
source_combined = ' '.join(reversed(sources))


# Define a Prompt.
SYSTEM_PROMPT = f"""Given the provided Context, your task is to
understand the content and accurately answer the question based
on the information available in the context. 
Provide a complete, clear, concise, relevant response in fewer
than 4 sentences and cite the unique Sources.
Answer: The answer to the question.
Sources: {source_combined}
Context: {contexts_combined}
"""


# Send the Question and Prompt to local! llama 3 chat.
import ollama
start_time = time.time()
response = ollama.chat(
   messages=[
       {"role": "system", "content": SYSTEM_PROMPT,},
       {"role": "user", "content": f"question: {SAMPLE_QUESTION}",}
   ],
   model='llama3',
   stream=False,
   options={"temperature": TEMPERATURE, "seed": RANDOM_SEED,
            "top_p": TOP_P,
           #  "max_tokens": MAX_TOKENS, # not recognized
            "frequency_penalty": FREQUENCY_PENALTY}
)


ollama_llama3_time = time.time() - start_time
pprint.pprint(response['message']['content'].replace('\n', ' '))
print(f"ollama_llama3_time: {format(ollama_llama3_time, '.2f')} seconds")

import openai


LLM_NAME = "meta-llama/Llama-3-70b-chat-hf"


anyscale_client = openai.OpenAI(
   base_url = "https://api.endpoints.anyscale.com/v1",
   api_key=os.environ.get("ANYSCALE_ENPOINT_KEY"),
)


start_time = time.time()
response = anyscale_client.chat.completions.create(
   messages=[
       {"role": "system", "content": SYSTEM_PROMPT,},
       {"role": "user", "content": f"question: {SAMPLE_QUESTION}",}
   ],
   model=LLM_NAME,
   temperature=TEMPERATURE,
   seed=RANDOM_SEED,
   frequency_penalty=FREQUENCY_PENALTY,
   top_p=TOP_P,
   max_tokens=MAX_TOKENS,
)
llama3_anyscale_endpoints_time = time.time() - start_time


# Print the response.
pprint.pprint(response.choices[0].message.content.replace('\n', ' '))
print(f"llama3_anyscale_endpoints_time: {format(llama3_anyscale_endpoints_time, '.2f')} seconds")

from octoai.text_gen import ChatMessage
from octoai.client import OctoAI


LLM_NAME = "meta-llama-3-70b-instruct"


octoai_client = OctoAI(
   api_key=os.environ.get("OCTOAI_TOKEN"),
)


start_time = time.time()
response = octoai_client.text_gen.create_chat_completion(
   messages=[
       ChatMessage(
           content=SYSTEM_PROMPT,
           role="system"
       ),
       ChatMessage(
           content=SAMPLE_QUESTION,
           role="user"
       )
   ],
   model=LLM_NAME,
   temperature=TEMPERATURE,
   # seed=RANDOM_SEED, # not recognized
   frequency_penalty=FREQUENCY_PENALTY,
   top_p=TOP_P,
   max_tokens=MAX_TOKENS,
)
llama3_octai_endpoints_time = time.time() - start_time


# Print the response.
pprint.pprint(response.choices[0].message.content.replace('\n', ' '))
print(f"llama3_octai_endpoints_time: {format(llama3_octai_endpoints_time, '.2f')} seconds")

from groq import Groq


LLM_NAME = "llama3-70b-8192"


groq_client = Groq(
   api_key=os.environ.get("GROQ_API_KEY"),
)


start_time = time.time()
response = groq_client.chat.completions.create(
   messages=[
       {"role": "system", "content": SYSTEM_PROMPT,},
       {"role": "user", "content": f"question: {SAMPLE_QUESTION}",}
   ],
   model=LLM_NAME,
   temperature=TEMPERATURE,
   seed=RANDOM_SEED,
   frequency_penalty=FREQUENCY_PENALTY,
   top_p=TOP_P,
   max_tokens=MAX_TOKENS,
)
llama3_groq_endpoints_time = time.time() - start_time


# Print the response.
pprint.pprint(response.choices[0].message.content.replace('\n', ' '))
print(f"llama3_groq_endpoints_time: {format(llama3_groq_endpoints_time, '.2f')} seconds")

import openai, pprint
from openai import OpenAI


LLM_NAME = "gpt-4o" # "gpt-3.5-turbo"


openai_client = OpenAI(
   # This is the default and can be omitted
   api_key=os.environ.get("OPENAI_API_KEY"),
)


start_time = time.time()
response = openai_client.chat.completions.create(
   messages=[
       {"role": "system", "content": SYSTEM_PROMPT,},
       {"role": "user", "content": f"question: {SAMPLE_QUESTION}",}
   ],
   model=LLM_NAME,
   temperature=TEMPERATURE,
   seed=RANDOM_SEED,
   frequency_penalty=FREQUENCY_PENALTY,
   top_p=TOP_P,
   max_tokens=MAX_TOKENS,
)
chatgpt_4o_turbo_time = time.time() - start_time


# Print the question and answer along with grounding sources and citations.
print(f"Question: {SAMPLE_QUESTION}")
for i, choice in enumerate(response.choices, 1):
   message = choice.message.content.replace('\n', '')
   pprint.pprint(f"Answer: {message}")
print(f"chatgpt_4o_turbo_time: {format(chatgpt_4o_turbo_time, '.5f')}")

import os, sys
import pandas as pd
import numpy as np
import ragas, datasets
from langchain_community.embeddings import HuggingFaceEmbeddings
from ragas.embeddings import LangchainEmbeddingsWrapper


from ragas.metrics import (
   # context_recall,
   # context_precision,
   # faithfulness,
   answer_relevancy,
   answer_similarity,
   answer_correctness
   )


# Read ground truth answers from file.
eval_df = pd.read_csv(file_path, header=0, skip_blank_lines=True)


# Possible LLM model choices to evaluate:
# openai gpt-4o = 'Custom_RAG_answer'
LLM_TO_EVALUATE = 'Custom_RAG_answer'
# LLM_TO_EVALUATE = 'llama3_ollama_answer'
# LLM_TO_EVALUATE = 'llama3_anyscale_answer'
# LLM_TO_EVALUATE = 'llama3_octoai_answer'
# LLM_TO_EVALUATE = 'llama3_groq_answer'
# LLM_TO_EVALUATE = 'mixtral_8x7b_anyscale_answer'


CONTEXT_TO_EVALUATE='Custom_RAG_context'
eval_metrics=[
    answer_relevancy,
    answer_similarity,
    answer_correctness,]
metrics = ['answer_relevancy', 'answer_similarity', 'answer_correctness']

# Change the default llm-as-critic, to save $.
LLM_NAME = "gpt-3.5-turbo"
ragas_llm = ragas.llms.llm_factory(model=LLM_NAME)


# Change the default embeddings to HuggingFace models.
EMB_NAME = "BAAI/bge-large-en-v1.5"
lc_embeddings = HuggingFaceEmbeddings(model_name=EMB_NAME)
ragas_emb = LangchainEmbeddingsWrapper(embeddings=lc_embeddings)


# Change each metric.
for metric in metrics:
   globals()[metric].llm = ragas_llm
   globals()[metric].embeddings = ragas_emb


# Execute the evaluation.
ragas_result, score = _eval_ragas.evaluate_ragas_model(
   eval_df, eval_metrics, LLM_TO_EVALUATE,
   CONTEXT_TO_EVALUATE, EVALUATE_WHAT)


# Display the results.
print(f"Using {eval_df.shape[0]} eval questions, Mean Score = {score}")
display(ragas_result.head())