# Install txtai
pip install txtai[graph] autoawq

from txtai import Embeddings

# Create embeddings instance with a semantic graph
embeddings = Embeddings({
  "autoid": "uuid5",
  "path": "intfloat/e5-base",
  "instructions": {
    "query": "query: ",
    "data": "passage: "
  },
  "content": True,
  "graph": {
      "approximate": False,
      "topics": {}
  }
})

# Load dataset
wikipedia = Embeddings()
wikipedia.load(provider="huggingface-hub", container="neuml/txtai-wikipedia")

query = """
SELECT id, text FROM txtai
order by percentile desc
LIMIT 100000
"""

embeddings.index(wikipedia.search(query))

graph = embeddings.search("Large Language Models", 50, graph=True)

import matplotlib.pyplot as plt
import networkx as nx

def plot(graph):
    labels = {x: f"{graph.attribute(x, 'id')} ({x})" for x in graph.scan()}
    options = {
        "node_size": 750,
        "node_color": "#0277bd",
        "edge_color": "#454545",
        "font_color": "#fff",
        "font_size": 6,
        "alpha": 1.0
    }

    fig, ax = plt.subplots(figsize=(17, 8))
    pos = nx.spring_layout(graph.backend, seed=0, k=0.9, iterations=50)
    nx.draw_networkx(graph.backend, pos=pos, labels=labels, **options)
    ax.set_facecolor("#303030")
    ax.axis("off")
    fig.set_facecolor("#303030")

    plt.show()

plot(graph)

for x in graph.showpath(49740, 96081):
    print(graph.node(x))

{'id': 'Linguistic relativity', 'text': "The idea of linguistic relativity, also known as the Sapir–Whorf hypothesis, the Whorf hypothesis, or Whorfianism, is a principle suggesting that the structure of a language influences its speakers' worldview or cognition, and thus individuals' languages determine or shape their perceptions of the world. ", 'topic': 'language_word_languages_also', 'topicrank': 5, 'score': 0.794975996017456}
{'id': 'Input hypothesis', 'text': 'The input hypothesis, also known as the monitor model, is a group of five hypotheses of second-language acquisition developed by the linguist Stephen Krashen in the 1970s and 1980s. Krashen originally formulated the input hypothesis as just one of the five hypotheses, but over time the term has come to refer to the five hypotheses as a group. The hypotheses are the input hypothesis, the acquisition–learning hypothesis, the monitor hypothesis, the natural order hypothesis and the affective filter hypothesis. The input hypothesis was first published in 1977.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 88, 'score': 0.7856757044792175}
{'id': 'Natural language processing', 'text': 'Natural language processing (NLP) is an interdisciplinary subfield of computer science and linguistics. It is primarily concerned with giving computers the ability to support and manipulate human language. It involves processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them. The technology can then accurately extract information and insights contained in the documents as well as categorize and organize the documents themselves.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 32, 'score': 0.7930917739868164}
{'id': 'ML (programming language)', 'text': 'ML (Meta Language) is a functional programming language. It is known for its use of the polymorphic Hindley–Milner type system, which automatically assigns the data types of most expressions without requiring explicit type annotations (type inference), and ensures type safety; there is a formal proof that a well-typed ML program does not cause runtime type errors. ML provides pattern matching for function arguments, garbage collection, imperative programming, call-by-value and currying. While a general-purpose programming language, ML is used heavily in programming language research and is one of the few languages to be completely specified and verified using formal semantics. Its types and pattern matching make it well-suited and commonly used to operate on other formal languages, such as in compiler writing, automated theorem proving, and formal verification.', 'topic': 'programming_language_computer_used', 'topicrank': 17, 'score': 0.7853577136993408}
{'id': 'Domain-specific language', 'text': 'A domain-specific language (DSL) is a computer language specialized to a particular application domain. This is in contrast to a general-purpose language (GPL), which is broadly applicable across domains. There are a wide variety of DSLs, ranging from widely used languages for common domains, such as HTML for web pages, down to languages used by only one or a few pieces of software, such as MUSH soft code. DSLs can be further subdivided by the kind of language, and include domain-specific markup languages, domain-specific modeling languages (more generally, specification languages), and domain-specific programming languages. Special-purpose computer languages have always existed in the computer age, but the term "domain-specific language" has become more popular due to the rise of domain-specific modeling. Simpler DSLs, particularly ones used by a single application, are sometimes informally called mini-languages.', 'topic': 'programming_language_computer_used', 'topicrank': 2, 'score': 0.7803027629852295}

for x in list(graph.centrality().keys())[:10]:
    print(graph.node(x))

{'id': 'Generative pre-trained transformer', 'text': 'Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. They are artificial neural networks that are used in natural language processing tasks. GPTs are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 11, 'score': 0.8267544507980347}
{'id': 'Large language model', 'text': 'A large language model (LLM) is a large-scale language model notable for its ability to achieve general-purpose language understanding and generation. LLMs acquire these abilities by using massive amounts of data to learn billions of parameters during training and consuming large computational resources during their training and operation. LLMs are artificial neural networks (mainly transformers) and are (pre)trained using self-supervised learning and semi-supervised learning.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 44, 'score': 0.9012120962142944}
{'id': 'Natural language processing', 'text': 'Natural language processing (NLP) is an interdisciplinary subfield of computer science and linguistics. It is primarily concerned with giving computers the ability to support and manipulate human language. It involves processing natural language datasets, such as text corpora or speech corpora, using either rule-based or probabilistic (i.e. statistical and, most recently, neural network-based) machine learning approaches. The goal is a computer capable of "understanding" the contents of documents, including the contextual nuances of the language within them. The technology can then accurately extract information and insights contained in the documents as well as categorize and organize the documents themselves.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 32, 'score': 0.7930917739868164}
{'id': 'BERT (language model)', 'text': 'Bidirectional Encoder Representations from Transformers (BERT) is a language model based on the transformer architecture, notable for its dramatic improvement over previous state of the art models. It was introduced in October 2018 by researchers at Google. A 2020 literature survey concluded that "in a little over a year, BERT has become a ubiquitous baseline in Natural Language Processing (NLP) experiments counting over 150 research publications analyzing and improving the model."', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 76, 'score': 0.8038361072540283}
{'id': 'GPT-4', 'text': 'Generative Pre-trained Transformer 4 (GPT-4) is a multimodal large language model created by OpenAI, and the fourth in its series of GPT foundation models. It was initially released on March 14, 2023, and has been made publicly available via the paid chatbot product ChatGPT Plus, and via OpenAI\'s API.  As a transformer-based model, GPT-4 uses a paradigm where pre-training using both public data and "data licensed from third-party providers" is used to predict the next token. After this step, the model was then fine-tuned with reinforcement learning feedback from humans and AI for human alignment and policy compliance.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 57, 'score': 0.808547854423523}
{'id': 'DALL-E', 'text': 'DALL·E, DALL·E 2, and DALL·E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions, called "prompts". ', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 79, 'score': 0.8013205528259277}
{'id': 'GPT-3', 'text': 'Generative Pre-trained Transformer 3 (GPT-3) is a large language model released by OpenAI in 2020. Like its predecessor, GPT-2, it is a decoder-only transformer model of deep neural network, which supersedes recurrence- and convolution-based architectures with a technique known as "attention". This attention mechanism allows the model to selectively focus on segments of input text it predicts to be most relevant. It uses a 2048-tokens-long context and a hitherto-unprecedented 175 billion parameters, requiring 800GB of storage space, and has demonstrated strong "zero-shot" and "few-shot" learning abilities on many tasks.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 53, 'score': 0.8063850998878479}
{'id': 'LLaMA', 'text': 'LLaMA (Large Language Model Meta AI) is a family of large language models (LLMs), released by Meta AI starting in February 2023. ', 'score': 0.8551499843597412}
{'id': 'LaMDA', 'text': "LaMDA (Language Model for Dialogue Applications) is a family of conversational large language models developed by Google. Originally developed and introduced as Meena in 2020, the first-generation LaMDA was announced during the 2021 Google I/O keynote, while the second generation was announced the following year. In June 2022, LaMDA gained widespread attention when Google engineer Blake Lemoine made claims that the chatbot had become sentient. The scientific community has largely rejected Lemoine's claims, though it has led to conversations about the efficacy of the Turing test, which measures whether a computer can pass for a human. In February 2023, Google announced Bard, a conversational artificial intelligence chatbot powered by LaMDA, to counter the rise of OpenAI's ChatGPT.", 'topic': 'artificial_learning_intelligence_based', 'topicrank': 67, 'score': 0.8128454089164734}
{'id': 'ChatGPT', 'text': 'ChatGPT (Chat Generative Pre-trained Transformer) is a chatbot developed by OpenAI and launched on November 30, 2022. Based on a large language model, it enables users to refine and steer a conversation towards a desired length, format, style, level of detail, and language. Successive prompts and replies, known as prompt engineering, are considered at each conversation stage as a context.', 'topic': 'artificial_learning_intelligence_based', 'topicrank': 72, 'score': 0.7816741466522217}

from txtai import LLM
llm = LLM("TheBloke/Mistral-7B-OpenOrca-AWQ")

def facts(graph):
    question = "List 5 facts from this text"
    text = "\n".join(graph.node(x)["text"] for x in list(graph.centrality().keys())[:10])

    prompt = f"""<|im_start|>system
    You are a friendly assistant. You answer questions from users.<|im_end|>
    <|im_start|>user
    Answer the following question using only the context below. Only include information specifically discussed.

    question: {question}
    context: {text} <|im_end|>
    <|im_start|>assistant
    """

    print(llm(prompt, maxlength=4096))

facts(graph)

1. GPTs are a type of large language model (LLM) and a prominent framework for generative artificial intelligence.
2. They are artificial neural networks used in natural language processing tasks and are based on the transformer architecture.
3. GPTs are pre-trained on large data sets of unlabelled text and can generate novel human-like content.
4. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.
5. LLMs acquire their abilities by using massive amounts of data to learn billions of parameters during training and consume large computational resources during their training and operation.

query = """
SELECT id, text FROM txtai
WHERE similar(:x)
LIMIT 5000
"""

embeddings.index(wikipedia.search(query, parameters={"x": "Vikings in the middle ages"}))

graph = embeddings.search("Viking raids in Ireland", 50, graph=True)
plot(graph)

facts(graph)

1. The Battle of Tara was fought between the Gaelic Irish of Meath, led by Máel Sechnaill mac Domnaill, and the Norse Vikings of Dublin, led by Amlaíb Cuarán, in 980 near the Hill of Tara in Ireland.
2. The Vikings had formed temporary alliances with certain Irish clans between 950-980 AD, which allowed them to continue their raids and plunder of the island.
3. The Battle of Tara was a devastating defeat for the Vikings, leading to the Irish regaining control of Dublin.
4. The First Viking Age in Ireland began in 795 with Viking raiders targeting Gaelic Irish coastal settlements.
5. The Norse Kingdom of Dublin, the earliest and longest-lasting Norse kingdom in Ireland, was established by Vikings in the 9th century and became the biggest slave port in Western Europe under their rule.

embeddings.index(wikipedia.search(query, parameters={"x": "Roman Empire"}))

graph = embeddings.search("Roman soldiers", 50, graph=True)
plot(graph)

facts(graph)

1. Vexillarius is a term referring to a type of Roman soldier.
2. A numerus was a unit of the Roman army.
3. Roman legionaries were professional heavy infantrymen who conquered and defended territories during the late Republic and Principate eras.
4. Comitatenses and later Palatini were units of the field armies of the late Roman Empire, replacing the legionaries.
5. A hastiliarius was a weapons instructor in the Roman Empire who trained troops in standard weapons and fighting techniques.

# Load dataset
arxiv = Embeddings()
arxiv.load(provider="huggingface-hub", container="neuml/txtai-arxiv")

query = """
SELECT id, text FROM txtai
WHERE similar(:x)
LIMIT 1000
"""

embeddings.index(arxiv.search(query, parameters={"x": "Retrieval-Augmented Generation"}))

graph = embeddings.search("Best ways to populate context", 50, graph=True)
plot(graph)

facts(graph)

1. Context Tuning for Retrieval Augmented Generation (RAG) improves tool retrieval and plan generation by employing a smart context retrieval system to fetch relevant information.
2. Synthetic Data Generation in Low-Resource Settings via Fine-Tuning of Large Language Models aims to improve downstream performance of smaller models by generating synthetic data.
3. Query Expansion by Prompting Large Language Models leverages the generative abilities of LLMs for query expansion using prompts like zero-shot, few-shot, and Chain-of-Thought (CoT).
4. In-Context Retrieval-Augmented Language Models prepend grounding documents to the input without modifying the LM architecture, providing significant LM gains across model sizes and diverse corpora.
5. Generate rather than Retrieve: Large Language Models are Strong Context Generators proposes a generate-then-read (GenRead) method that prompts a large language model to generate context-based documents for answering questions.

embeddings.index(arxiv.search(query, parameters={"x": "Alien life"}))

graph = embeddings.search("Alien encounters on Earth", 50, graph=True)
plot(graph)

facts(graph)

1. Earth has been thoroughly surveilled.
2. Earth will be contacted in due course.
3. SETI beyond half the distance that Earth's EM has reached (~35-50 LY) is futile.
4. The very quiescence of the galaxy paradoxically implies that that Drake's N = many, and that there is a system of galactic governance.
5. Search strategies are proposed to detect the described probe-node-land base communications pathway.

def topic(graph):
    topic = list(graph.topics.keys())[0]

    text = "\n".join(graph.node(x)["text"] for x in graph.topics[topic])

    prompt = f"""<|im_start|>system
    You are a friendly assistant. You answer questions from users.<|im_end|>
    <|im_start|>user
    Label the following text with a topic name in a couple words.

    text: {text}
    topic: <|im_end|>
    <|im_start|>assistant
    """

    print(f"Topic: \"{topic}\", Generated Topic: \"{llm(prompt, maxlength=4096)}\"")

topic(graph)

Topic: "often_space_we_earth", Generated Topic: "UFOs and Alien Encounters"