from txtai import Agent, Embeddings

from txtai.pipeline import Textractor

from txtai.workflow import Workflow, Task



# Empty embeddings database

embeddings = Embeddings(

    path="intfloat/e5-large",

    instructions={"query": "query: ", "data": "passage: "},

    content=True

)



# Textractor instance

textractor = Textractor(sections=True, headers={"user-agent": "Mozilla/5.0"})



def insert(elements):

    """

    Inserts elements into the embeddings database.



    Args:

        elements: list of strings to insert

    """



    def upsert(elements):

        embeddings.upsert(elements)

        return elements



    # Upsert workflow

    workflow = Workflow([Task(textractor), Task(upsert)])

    list(workflow(elements))

    return f"{elements} inserted successfully"



agent = Agent(

    tools=[insert, embeddings.search, "websearch"],

    llm="Qwen/Qwen2.5-7B-Instruct-AWQ",

    max_iterations=10

)

prompt = """

Run the following process:

 1. Search your internal knowledge for {topic}

 2. If not found, find relevant urls and insert those as a list of strings ONLY. Then rerun the search for {topic}.

 3. Write a detailed report about {topic} with Markdown sections covering the major topics. Include a section with hyperlink references.

"""



answer = agent(prompt.format(topic="txtai"))

display(Markdown(answer))

======== New task ========



Run the following process:

 1. Search your internal knowledge for txtai

 2. If not found, find relevant urls and insert those as a list of strings ONLY. Then rerun the search for txtai.

 3. Write a detailed report about txtai with Markdown sections covering the major topics. Include a section with hyperlink references.



=== Agent thoughts:

Thought: First, I will attempt to search for "txtai" in my internal knowledge base.

>>> Calling tool: 'search' with arguments: {'query': 'txtai'}

=== Agent thoughts:

Thought: Since the search for "txtai" did not yield any results, I will proceed to find relevant URLs and insert them as a list of strings.

>>> Calling tool: 'web_search' with arguments: {'query': 'txtai'}

=== Agent thoughts:

Thought: Now that I have found relevant URLs, I will insert them into the database as a list of strings.

>>> Calling tool: 'insert' with arguments: {'elements': ['https://github.com/neuml/txtai', 'https://pypi.org/project/txtai/', 'https://neuml.github.io/txtai/', 'https://neuml.com/', 'https://medium.com/neuml/introducing-txtai-the-all-in-one-embeddings-database-c721f4ff91ad', 'https://neuml.github.io/txtai/embeddings/', 'https://neuml.github.io/txtai/examples/']}

=== Agent thoughts:

Thought: Now that the relevant URLs have been inserted, I will rerun the search for "txtai".

>>> Calling tool: 'search' with arguments: {'query': 'txtai'}

=== Agent thoughts:

>>> Calling tool: 'final_answer' with arguments: {'answer': '# txtai Overview\n\ntxtai is an all-in-one open-source embeddings database designed for semantic search, LLM orchestration, and language model workflows. It combines vector indexes (both sparse and dense), graph networks, and relational databases to offer a comprehensive solution for various tasks.\n\n## Semantic Search\n\ntxtai supports semantic search, enabling users to find relevant information based on the meaning of the text rather than just keywords. This makes it suitable for applications such as recommendation systems, content retrieval, and more.\n\n## LLM Orchestration\n\ntxtai includes support for Large Language Models (LLMs) orchestration, which allows users to integrate and manage different LLMs within their workflows. This feature is particularly useful for tasks such as prompt chaining, summarization, transcription, translation, and more.\n\n## Embeddings Databases\n\ntxtai provides a unified interface for embedding, indexing, searching, and processing text and multimedia data. Users can create, index, and search embeddings using code snippets and examples provided in the documentation.\n\n## Hyperlink References\n\n- [txtai on GitHub](https://github.com/neuml/txtai)\n- [PyPI - txtai](https://pypi.org/project/txtai/)\n- [txtai Documentation](https://neuml.github.io/txtai/)\n- [txtai Examples](https://neuml.github.io/txtai/examples/)\n- [txtai Embeddings](https://neuml.github.io/txtai/embeddings/)'}