metadata

title: Indian Budget RAGBot
emoji: 👀
colorFrom: green
colorTo: gray
sdk: gradio
sdk_version: 4.40.0
app_file: app.py
pinned: false
short_description: Boost NLP with MonsterAPI and Haystack.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

MonsterAPI Integration with Haystack

Overview

MonsterAPI offers powerful language models designed to handle various text-generation tasks with high efficiency. By integrating MonsterAPI with the Haystack framework, users can enhance their natural language processing capabilities, utilizing advanced models for improved performance in search, question answering, and more.

To get started, sign up for an API key here. New users receive 2500 FREE credits upon signing up, enabling you to explore MonsterAPI’s features and capabilities without incurring initial costs.

Benefits of Using MonsterAPI with Haystack

The integration of MonsterAPI with Haystack brings several advantages:

Advanced Language Models: Access to state-of-the-art models that excel in generating and understanding text.
Seamless Integration: MonsterAPI's API is compatible with OpenAI's API, allowing easy integration into Haystack's pipeline.
Enhanced Functionality: Leverage the strengths of both Haystack’s framework and MonsterAPI’s models for more robust and accurate NLP solutions.

Usage

Using `Generator`

Here’s how you can use a model served via MonsterAPI to perform question answering on a web page with Haystack:

Set the environment variable MONSTER_API_KEY.
Choose a compatible model.

from haystack import Pipeline
from haystack.utils import Secret
from haystack.components.fetchers import LinkContentFetcher
from haystack.components.converters import HTMLToDocument
from haystack.components.builders import PromptBuilder
from haystack.components.generators import OpenAIGenerator

fetcher = LinkContentFetcher()
converter = HTMLToDocument()
prompt_template = """
According to the contents of this website:
{% for document in documents %}
  {{document.content}}
{% endfor %}
Answer the given question: {{query}}
Answer:
"""
prompt_builder = PromptBuilder(template=prompt_template)
llm = OpenAIGenerator(
    api_key=Secret.from_env_var("MONSTER_API_KEY"),
    api_base_url="https://llm.monsterapi.ai/v1/",
    model="microsoft/Phi-3-mini-4k-instruct",
    generation_kwargs={"max_tokens": 256}
)
pipeline = Pipeline()
pipeline.add_component("fetcher", fetcher)
pipeline.add_component("converter", converter)
pipeline.add_component("prompt", prompt_builder)
pipeline.add_component("llm", llm)

pipeline.connect("fetcher.streams", "converter.sources")
pipeline.connect("converter.documents", "prompt.documents")
pipeline.connect("prompt.prompt", "llm.prompt")

result = pipeline.run({"fetcher": {"urls": ["https://developer.monsterapi.ai/docs/"]},
              "prompt": {"query": "What are the features of MonsterAPI?"}})

print(result["llm"]["replies"][0])

Using `ChatGenerator`

To engage in a multi-turn conversation with a MonsterAPI model, follow this example:

Set the environment variable MONSTER_API_KEY.
Choose a compatible model.

from haystack.components.generators.chat import OpenAIChatGenerator
from haystack.dataclasses import ChatMessage
from haystack.utils import Secret

generator = OpenAIChatGenerator(
    api_key=Secret.from_env_var("MONSTER_API_KEY"),
    api_base_url="https://llm.monsterapi.ai/v1/",
    model="microsoft/Phi-3-mini-4k-instruct",
    generation_kwargs={"max_tokens": 256}
)

messages = []

while True:
    msg = input("Enter your message or Q to exit\n ")
    if msg == "Q":
        break
    messages.append(ChatMessage.from_user(msg))
    response = generator.run(messages=messages)
    assistant_resp = response['replies'][0]
    print(assistant_resp.content)
    messages.append(assistant_resp)

Resources

Getting Help

For any questions or support, please refer to the Haystack documentation or contact the MonsterAPI support team.