|
import gradio as gr |
|
|
|
from haystack.components.generators import HuggingFaceTGIGenerator |
|
|
|
generator = HuggingFaceTGIGenerator("mistralai/Mixtral-8x7B-Instruct-v0.1") |
|
generator.warm_up() |
|
|
|
from haystack.components.fetchers.link_content import LinkContentFetcher |
|
from haystack.components.converters import HTMLToDocument |
|
from haystack.components.preprocessors import DocumentSplitter |
|
from haystack.components.rankers import TransformersSimilarityRanker |
|
from haystack.components.generators import GPTGenerator |
|
from haystack.components.builders.prompt_builder import PromptBuilder |
|
from haystack import Pipeline |
|
|
|
fetcher = LinkContentFetcher() |
|
converter = HTMLToDocument() |
|
document_splitter = DocumentSplitter(split_by="word", split_length=50) |
|
similarity_ranker = TransformersSimilarityRanker(top_k=3) |
|
|
|
prompt_template = """ |
|
According to these documents: |
|
{% for doc in documents %} |
|
{{ doc.content }} |
|
{% endfor %} |
|
Answer the given question: {{question}} |
|
Answer: |
|
""" |
|
prompt_builder = PromptBuilder(template=prompt_template) |
|
|
|
pipeline = Pipeline() |
|
pipeline.add_component("fetcher", fetcher) |
|
pipeline.add_component("converter", converter) |
|
pipeline.add_component("splitter", document_splitter) |
|
pipeline.add_component("ranker", similarity_ranker) |
|
pipeline.add_component("prompt_builder", prompt_builder) |
|
pipeline.add_component("llm", generator) |
|
|
|
pipeline.connect("fetcher.streams", "converter.sources") |
|
pipeline.connect("converter.documents", "splitter.documents") |
|
pipeline.connect("splitter.documents", "ranker.documents") |
|
pipeline.connect("ranker.documents", "prompt_builder.documents") |
|
pipeline.connect("prompt_builder.prompt", "llm.prompt") |
|
|
|
def respond(prompt, use_rag): |
|
if use_rag: |
|
result = pipeline.run({"prompt_builder": {"question": prompt}, |
|
"ranker": {"query": prompt}, |
|
"fetcher": {"urls": ["https://haystack.deepset.ai/blog/introducing-haystack-2-beta-and-advent"]}, |
|
"llm":{"generation_kwargs": {"max_new_tokens": 350}}}) |
|
return result['llm']['replies'][0] |
|
else: |
|
result = generator.run(prompt, generation_kwargs={"max_new_tokens": 350}) |
|
return result["replies"][0] |
|
|
|
iface = gr.Interface(fn=respond, inputs=["text", "checkbox"], outputs="text") |
|
iface.launch() |