Integration: STACKIT

pip install stackit-haystack

import os
from haystack.dataclasses import ChatMessage
from haystack_integrations.components.generators.stackit import STACKITChatGenerator

os.environ["STACKIT_API_KEY"] = "YOUR_STACKIT_API_KEY"

generator = STACKITChatGenerator(model="neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8")

result = generator.run([ChatMessage.from_user("Tell me a joke.")])
print(result)

{'replies': [ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>, _content=[TextContent(text='A man walked into a library and asked the librarian, "Do you have any books on Pavlov\'s dogs and Schrödinger\'s cat?" \n\nThe librarian replied, "It rings a bell, but I\'m not sure if it\'s here or not."')], _name=None, _meta={'model': 'neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8', 'index': 0, 'finish_reason': 'stop', 'usage': {'completion_tokens': 55, 'prompt_tokens': 40, 'total_tokens': 95, 'completion_tokens_details': None, 'prompt_tokens_details': None}})]}

import os

from haystack.components.generators.utils import print_streaming_chunk
from haystack.dataclasses import ChatMessage
from haystack_integrations.components.generators.stackit import STACKITChatGenerator

os.environ["STACKIT_API_KEY"] = "YOUR_STACKIT_API_KEY"

client = STACKITChatGenerator(
    model="neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8",
    streaming_callback=print_streaming_chunk
)

response = client.run(
    messages=[ChatMessage.from_user("Tell me a joke.")]
)
print(response)

{'replies': [ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>, _content=[TextContent(text='What do you call a fake noodle?\n\nAn impasta.')], _name=None, _meta={'model': 'neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8', 'index': 0, 'finish_reason': 'stop', 'completion_start_time': '2025-02-27T20:54:57.006032', 'usage': {}})]}

import os

from haystack import Document, Pipeline
from haystack.components.writers import DocumentWriter
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack_integrations.components.embedders.stackit import STACKITDocumentEmbedder

os.environ["STACKIT_API_KEY"] = "YOUR_STACKIT_API_KEY"

document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")

documents = [Document(content="My name is Wolfgang and I live in Berlin"),
             Document(content="I saw a black horse running"),
             Document(content="Germany has many big cities")]

embedder = STACKITDocumentEmbedder(model="intfloat/e5-mistral-7b-instruct")
writer = DocumentWriter(document_store=document_store)

indexing_pipeline = Pipeline()
indexing_pipeline.add_component(name="embedder", instance=embedder)
indexing_pipeline.add_component(name="writer", instance=writer)

indexing_pipeline.connect("embedder", "writer")

result = indexing_pipeline.run(data={"embedder": {"documents": documents}})

print(result)

{'embedder': {'meta': {}}, 'writer': {'documents_written': 3}}

import os

from haystack import Pipeline
from haystack.components.builders import ChatPromptBuilder
from haystack.dataclasses import ChatMessage

from haystack_integrations.components.generators.stackit import STACKITChatGenerator

os.environ["STACKIT_API_KEY"] = "YOUR_STACKIT_API_KEY"

prompt_builder = ChatPromptBuilder()
llm = STACKITChatGenerator(model="neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8")

messages = [ChatMessage.from_user("Question: {{question}} \\n")]

pipeline = Pipeline()
pipeline.add_component("prompt_builder", prompt_builder)
pipeline.add_component("llm", llm)

pipeline.connect("prompt_builder.prompt", "llm.messages")

result = pipeline.run({"prompt_builder": {"template_variables": {"question": "Tell me a joke."}, "template": messages}})

print(result)

{'llm': {'replies': [ChatMessage(_role=<ChatRole.ASSISTANT: 'assistant'>, _content=[TextContent(text="Why couldn't the bicycle stand up by itself? \n\nBecause it was two-tired.")], _name=None, _meta={'model': 'neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8', 'index': 0, 'finish_reason': 'stop', 'usage': {'completion_tokens': 19, 'prompt_tokens': 44, 'total_tokens': 63, 'completion_tokens_details': None, 'prompt_tokens_details': None}})]}}

import os

from haystack import Pipeline
from haystack.components.builders import ChatPromptBuilder
from haystack.components.converters import HTMLToDocument
from haystack.components.fetchers import LinkContentFetcher
from haystack.components.generators.utils import print_streaming_chunk
from haystack.components.preprocessors import DocumentSplitter
from haystack.components.retrievers import InMemoryEmbeddingRetriever
from haystack.components.writers import DocumentWriter
from haystack.dataclasses import ChatMessage
from haystack.document_stores.in_memory import InMemoryDocumentStore

from haystack_integrations.components.generators.stackit import STACKITChatGenerator
from haystack_integrations.components.embedders.stackit import STACKITDocumentEmbedder, STACKITTextEmbedder

os.environ["STACKIT_API_KEY"] = "YOUR_STACKIT_API_KEY"

document_store = InMemoryDocumentStore()
fetcher = LinkContentFetcher()
converter = HTMLToDocument()
chunker = DocumentSplitter()
doc_embedder = STACKITDocumentEmbedder(model="intfloat/e5-mistral-7b-instruct")
writer = DocumentWriter(document_store=document_store)

indexing = Pipeline()

indexing.add_component(name="fetcher", instance=fetcher)
indexing.add_component(name="converter", instance=converter)
indexing.add_component(name="chunker", instance=chunker)
indexing.add_component(name="doc_embedder", instance=doc_embedder)
indexing.add_component(name="writer", instance=writer)

indexing.connect("fetcher", "converter")
indexing.connect("converter", "chunker")
indexing.connect("chunker", "doc_embedder")
indexing.connect("doc_embedder", "writer")

indexing.run(data={"fetcher": {"urls": ["https://www.stackit.de/en/"]}})

text_embedder = STACKITTextEmbedder(model="intfloat/e5-mistral-7b-instruct")
retriever = InMemoryEmbeddingRetriever(document_store=document_store)
prompt_builder = ChatPromptBuilder(variables=["documents"])
llm = STACKITChatGenerator(model="neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8", streaming_callback=print_streaming_chunk)

messages = [ChatMessage.from_user("Here are some of the documents: {{documents}} \\n Question: {{query}} \\n Answer:")]

rag_pipeline = Pipeline()
rag_pipeline.add_component("text_embedder", text_embedder)
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", prompt_builder)
rag_pipeline.add_component("llm", llm)

rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
rag_pipeline.connect("retriever.documents", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder.prompt", "llm.messages")

question = "What does STACKIT offer?"

result = rag_pipeline.run(
    {
        "text_embedder": {"text": question},
        "prompt_builder": {"template_variables": {"query": question}, "template": messages},
        "llm": {"generation_kwargs": {"max_tokens": 165}},
    }
)

print(result)

STACKIT offers high-performance data centers, scalable cloud solutions, and colocation services.