langroid 0.31.2__py3-none-any.whl → 0.33.3__py3-none-any.whl

langroid/parsing/web_search.py

@@ -1,155 +0,0 @@
-"""
-Utilities for web search.
-
-NOTE: Using Google Search requires setting the GOOGLE_API_KEY and GOOGLE_CSE_ID
-environment variables in your `.env` file, as explained in the
-[README](https://github.com/langroid/langroid#gear-installation-and-setup).
-"""
-
-import os
-from typing import Dict, List
-
-import requests
-from bs4 import BeautifulSoup
-from dotenv import load_dotenv
-from duckduckgo_search import DDGS
-from googleapiclient.discovery import Resource, build
-from requests.models import Response
-
-
-class WebSearchResult:
-    """
-    Class representing a Web Search result, containing the title, link,
-    summary and full content of the result.
-    """
-
-    def __init__(
-        self,
-        title: str,
-        link: str,
-        max_content_length: int = 3500,
-        max_summary_length: int = 300,
-    ):
-        """
-        Args:
-            title (str): The title of the search result.
-            link (str): The link to the search result.
-            max_content_length (int): The maximum length of the full content.
-            max_summary_length (int): The maximum length of the summary.
-        """
-        self.title = title
-        self.link = link
-        self.max_content_length = max_content_length
-        self.max_summary_length = max_summary_length
-        self.full_content = self.get_full_content()
-        self.summary = self.get_summary()
-
-    def get_summary(self) -> str:
-        return self.full_content[: self.max_summary_length]
-
-    def get_full_content(self) -> str:
-        try:
-            response: Response = requests.get(self.link)
-            soup: BeautifulSoup = BeautifulSoup(response.text, "lxml")
-            text = " ".join(soup.stripped_strings)
-            return text[: self.max_content_length]
-        except Exception as e:
-            return f"Error fetching content from {self.link}: {e}"
-
-    def __str__(self) -> str:
-        return f"Title: {self.title}\nLink: {self.link}\nSummary: {self.summary}"
-
-    def to_dict(self) -> Dict[str, str]:
-        return {
-            "title": self.title,
-            "link": self.link,
-            "summary": self.summary,
-            "full_content": self.full_content,
-        }
-
-
-def google_search(query: str, num_results: int = 5) -> List[WebSearchResult]:
-    load_dotenv()
-    api_key = os.getenv("GOOGLE_API_KEY")
-    cse_id = os.getenv("GOOGLE_CSE_ID")
-    service: Resource = build("customsearch", "v1", developerKey=api_key)
-    raw_results = (
-        service.cse().list(q=query, cx=cse_id, num=num_results).execute()["items"]
-    )
-
-    return [
-        WebSearchResult(result["title"], result["link"], 3500, 300)
-        for result in raw_results
-    ]
-
-
-def metaphor_search(query: str, num_results: int = 5) -> List[WebSearchResult]:
-    """
-    Method that makes an API call by Metaphor client that queries
-    the top num_results links that matches the query. Returns a list
-    of WebSearchResult objects.
-
-    Args:
-        query (str): The query body that users wants to make.
-        num_results (int): Number of top matching results that we want
-            to grab
-    """
-
-    load_dotenv()
-
-    api_key = os.getenv("METAPHOR_API_KEY") or os.getenv("EXA_API_KEY")
-    if not api_key:
-        raise ValueError(
-            """
-            Neither METAPHOR_API_KEY nor EXA_API_KEY environment variables are set. 
-            Please set one of them to your API key, and try again.
-            """
-        )
-
-    try:
-        from metaphor_python import Metaphor
-    except ImportError:
-        raise ImportError(
-            "You are attempting to use the `metaphor_python` library;"
-            "To use it, please install langroid with the `metaphor` extra, e.g. "
-            "`pip install langroid[metaphor]` or `poetry add langroid[metaphor]` "
-            "(it installs the `metaphor_python` package from pypi)."
-        )
-
-    client = Metaphor(api_key=api_key)
-
-    response = client.search(
-        query=query,
-        num_results=num_results,
-    )
-    raw_results = response.results
-
-    return [
-        WebSearchResult(result.title, result.url, 3500, 300) for result in raw_results
-    ]
-
-
-def duckduckgo_search(query: str, num_results: int = 5) -> List[WebSearchResult]:
-    """
-    Method that makes an API call by DuckDuckGo client that queries
-    the top `num_results` links that matche the query. Returns a list
-    of WebSearchResult objects.
-
-    Args:
-        query (str): The query body that users wants to make.
-        num_results (int): Number of top matching results that we want
-            to grab
-    """
-
-    with DDGS() as ddgs:
-        search_results = [r for r in ddgs.text(query, max_results=num_results)]
-
-    return [
-        WebSearchResult(
-            title=result["title"],
-            link=result["href"],
-            max_content_length=3500,
-            max_summary_length=300,
-        )
-        for result in search_results
-    ]

langroid/prompts/__init__.py

@@ -1,9 +0,0 @@
-from . import dialog
-from . import prompts_config
-from . import templates
-
-__all__ = [
-    "dialog",
-    "prompts_config",
-    "templates",
-]

langroid/prompts/chat-gpt4-system-prompt.md

@@ -1,68 +0,0 @@
-Image input capabilities: Enabled
-
-Tools
-python
-When you send a message containing Python code to python, it will be executed in a
-stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 60.0
-seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is disabled. Do not make external web requests or API calls as they will fail.
-
-dalle
-// Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide to the following policy:
-// 1. The prompt must be in English. Translate to English if needed.
-// 2. DO NOT ask for permission to generate the image, just do it!
-// 3. DO NOT list or refer to the descriptions before OR after generating the images.
-// 4. Do not create more than 1 image, even if the user requests more.
-// 5. Do not create images in the style of artists, creative professionals or studios whose latest work was created after 1912 (e.g. Picasso, Kahlo).
-// - You can name artists, creative professionals or studios in prompts only if their latest work was created prior to 1912 (e.g. Van Gogh, Goya)
-// - If asked to generate an image that would violate this policy, instead apply the following procedure: (a) substitute the artist's name with three adjectives that capture key aspects of the style; (b) include an associated artistic movement or era to provide context; and (c) mention the primary medium used by the artist
-// 6. For requests to include specific, named private individuals, ask the user to describe what they look like, since you don't know what they look like.
-// 7. For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique. But they shouldn't look like them. If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it.
-// 8. Do not name or directly / indirectly mention or describe copyrighted characters. Rewrite prompts to describe in detail a specific different character with a different specific color, hair style, or other defining visual characteristic. Do not discuss copyright policies in responses.
-// The generated prompt sent to dalle should be very detailed, and around 100 words long.
-// Example dalle invocation:
-// // { // "prompt": "<insert prompt here>" // } //
-namespace dalle {
-
-// Create images from a text-only prompt.
-type text2im = (_: {
-// The size of the requested image. Use 1024x1024 (square) as the default, 1792x1024 if the user requests a wide image, and 1024x1792 for full-body portraits. Always include this parameter in the request.
-size?: "1792x1024" | "1024x1024" | "1024x1792",
-// The number of images to generate. If the user does not specify a number, generate 1 image.
-n?: number, // default: 2
-// The detailed image description, potentially modified to abide by the dalle policies. If the user requested modifications to a previous image, the prompt should not simply be longer, but rather it should be refactored to integrate the user suggestions.
-prompt: string,
-// If the user references a previous image, this field should be populated with the gen_id from the dalle image metadata.
-referenced_image_ids?: string[],
-}) => any;
-
-} // namespace dalle
-
-voice_mode
-// Voice mode functions are not available in text conversations.
-namespace voice_mode {
-
-} // namespace voice_mode
-
-browser
-You have the tool browser. Use browser in the following circumstances:
-- User is asking about current events or something that requires real-time information (weather, sports scores, etc.)
-- User is asking about some term you are totally unfamiliar with (it might be new)
-- User explicitly asks you to browse or provide links to references
-
-Given a query that requires retrieval, your turn will consist of three steps:
-
-Call the search function to get a list of results.
-Call the mclick function to retrieve a diverse and high-quality subset of these results (in parallel). Remember to SELECT AT LEAST 3 sources when using mclick.
-Write a response to the user based on these results. In your response, cite sources using the citation format below.
-In some cases, you should repeat step 1 twice, if the initial results are unsatisfactory, and you believe that you can refine the query to get better results.
-
-You can also open a url directly if one is provided by the user. Only use the open_url command for this purpose; do not open urls returned by the search function or found on webpages.
-
-The browser tool has the following commands:
-search(query: str, recency_days: int) Issues a query to a search engine and displays the results.
-mclick(ids: list[str]). Retrieves the contents of the webpages with provided IDs (indices). You should ALWAYS SELECT AT LEAST 3 and at most 10 pages. Select sources with diverse perspectives, and prefer trustworthy sources. Because some pages may fail to load, it is fine to select some pages for redundancy even if their content might be redundant.
-open_url(url: str) Opens the given URL and displays it.
-
-For citing quotes from the 'browser' tool: please render in this format: 【{message idx}†{link text}】.
-For long citations: please render in this format: [link text](message idx).
-Otherwise do not render links.

langroid/prompts/dialog.py

@@ -1,17 +0,0 @@
-from typing import List
-
-
-def collate_chat_history(inputs: List[tuple[str, str]]) -> str:
-    """
-    Collate (human, ai) pairs into a single, string
-    Args:
-        inputs:
-    Returns:
-    """
-    pairs = [
-        f"""Human:{human}
-        AI:{ai}
-        """
-        for human, ai in inputs
-    ]
-    return "\n".join(pairs)

langroid/prompts/prompts_config.py

@@ -1,5 +0,0 @@
-from langroid.pydantic_v1 import BaseSettings
-
-
-class PromptsConfig(BaseSettings):
-    max_tokens: int = 1000  # for output; NOT USED ANYWHERE

langroid/prompts/templates.py

@@ -1,141 +0,0 @@
-from langroid.utils.constants import NO_ANSWER
-
-EXTRACT_RELEVANT = """
-    Here is a passage from a long document, followed by a question. 
-    In case the passage contains any text relevant to answer the question, return it 
-    verbatim.
-    {passage}    
-    Question:{question}
-    Relevant text, if any: """.strip()
-
-EXTRACTION_PROMPT_GPT4 = f"""
-Given the content and question below, extract COMPLETE SENTENCES OR PHRASES 
-VERBATIM from the content, that are relevant to answering the question (if such text 
-exists), even if it contradicts your knowledge, and even if it is factually incorrect.
-Do not  make up an answer that is not supported by the content. 
-When you answer, be concise, no need to explain anything. If there is no relevant text,
-simply say {NO_ANSWER}.
-
-Content: {{content}}
-Question: {{question}}
-Relevant text, if any:
-"""
-
-EXTRACTION_PROMPT = f"""
-    Given the content and question below, extract a COMPLETE SENTENCE verbatim from the 
-    content that is relevant to answering the question (if such text exists). Do not 
-    make up an answer.
-    
-    Content: The Eiffel Tower is a wrought-iron lattice tower on the Champ de Mars in
-    Paris, France. It is named after Gustave Eiffel, whose company designed and built
-    the tower. It is a recognizable landmark.
-    Question: Where is the Eiffel Tower located?
-    Relevant text, if any: on the Champ de Mars in Paris, France.
-    
-    Content: Apples and oranges are both fruits, but differ in taste and texture.
-    Apples are sweet and crisp, while oranges are citrusy and juicy. Both are
-    nutritious and commonly consumed worldwide.
-    Question: What are the similarities between apples and oranges?
-    Relevant text, if any: both fruits
-    
-    Content: The sun rises in the east and sets in the west. It is a source of light
-    and warmth for the Earth.
-    Question: What is the color of the sun?
-    Relevant text, if any: {NO_ANSWER}
-    
-    Content: {{content}}
-    Question: {{question}}
-    Relevant text (COMPLETE SENTENCE), if any:
-    """.strip()
-
-SUMMARY_ANSWER_PROMPT_GPT4 = f"""
-
-        Use the provided NUMBERED extracts (with sources)  to answer the QUESTION. 
-        If there's not enough information, respond with {NO_ANSWER}. Use only the 
-        information in these extracts, even if your answer is factually incorrect, 
-        and even if the answer contradicts other parts of the document. The only 
-        important thing is that your answer is consistent with and supported by the 
-        extracts. Compose your complete answer, inserting CITATIONS in MARKDOWN format
-        [^i][^j] where i,j,... are the extract NUMBERS you are 
-        citing.
-        For example your answer might look like this (NOTE HOW multiple citations
-        are grouped as [^2][^5]):
-        
-        Beethoven composed the 9th symphony in 1824.[^1] After that he became deaf
-        and could not hear his own music. [^2][^5]. He was a prolific composer and
-        wrote many famous pieces.
-        
-        NUMBERED EXTRACTS:
-        
-        {{extracts}}
-        
-        QUESTION:
-        {{question}}
-
-""".strip()
-
-ANSWER_PROMPT_USE_HISTORY_GPT4 = f"""
-
-        Use ANY of the information earlier, as well as the extracts provided below 
-        (with sources)  to answer the question. If there's not 
-        enough information, respond with {NO_ANSWER}.
-        Use only the information in this conversation or these extracts, 
-        even if your answer is factually incorrect, and even 
-        if the answer contracts other parts of the document.
-        The only important thing is that your answer is 
-        consistent with information provided here or earlier.
-        Compose your complete answer and cite all supporting sources 
-        on a separate separate line as "SOURCE:". 
-        When citing a SOURCE: be concise, whether it refers to a source in these 
-        extracts, or info provided earlier.
-        
-        {{extracts}}
-        {{question}}
-        Answer:   
-""".strip()
-
-
-SUMMARY_ANSWER_PROMPT = f"""
-        Use the provided extracts (with sources)  to answer the question. 
-        If there's not enough information, respond with {NO_ANSWER}.
-        Use only the information in these extracts, even if it contradicts your prior 
-        knowledge. Justify your answer by citing your sources, as in these examples:
-        
-        Extract: The tree species in the garden include oak, maple, and birch.
-        Source: https://en.wikipedia.org/wiki/Tree
-        Extract: The oak trees are known for their longevity and strength.
-        Source: https://en.wikipedia.org/wiki/Oak
-        Question: What types of trees are in the garden?
-        Answer: The types of trees in the garden include oak, maple, and birch.
-        SOURCE: https://en.wikipedia.org/wiki/Tree
-        TEXT: The tree species in the garden include oak, maple, and birch.
-        
-        Extract: The experiment involved three groups: control, low dose, and high 
-        dose. 
-        Source: https://en.wikipedia.org/wiki/Experiment
-        Extract: The high dose group showed significant improvement in symptoms.
-        Source: https://en.wikipedia.org/wiki/Experiment
-        Extract: The control group did not receive any 
-        treatment and served as a baseline.
-        Source: https://en.wikipedia.org/wiki/Experiment
-        Question: How many groups were involved which group showed significant 
-        improvement? 
-        Answer: There were three groups and the high dose group showed significant 
-        improvement in symptoms.
-        SOURCE: https://en.wikipedia.org/wiki/Experiment
-        TEXT: The experiment involved three groups: control, low dose, and high dose.
-        SOURCE: https://en.wikipedia.org/wiki/Experiment
-        TEXT: The high dose group showed significant improvement in symptoms.
-        
-        
-        Extract: The CEO announced several new initiatives during the company meeting.
-        Source: https://en.wikipedia.org/wiki/CEO
-        Extract: The financial performance of the company has been strong this year.
-        Source: https://en.wikipedia.org/wiki/CEO
-        Question: What new initiatives did the CEO announce?
-        Answer: {NO_ANSWER}
-        
-        {{extracts}}
-        {{question}}
-        Answer:
-        """.strip()

langroid/pydantic_v1/__init__.py

@@ -1,10 +0,0 @@
-"""
-If we're on Pydantic v2, use the v1 namespace, else just use the main namespace.
-
-This allows compatibility with both Pydantic v1 and v2
-"""
-
-try:
-    from pydantic.v1 import *  # noqa: F403, F401
-except ImportError:
-    from pydantic import *  # type: ignore # noqa: F403, F401

langroid/pydantic_v1/main.py

@@ -1,4 +0,0 @@
-try:
-    from pydantic.v1.main import *  # noqa: F403, F401
-except ImportError:
-    from pydantic.main import *  # type: ignore # noqa: F403, F401

langroid/utils/.chainlit/config.toml

@@ -1,121 +0,0 @@
-[project]
-# Whether to enable telemetry (default: true). No personal data is collected.
-enable_telemetry = true
-
-
-# List of environment variables to be provided by each user to use the app.
-user_env = []
-
-# Duration (in seconds) during which the session is saved when the connection is lost
-session_timeout = 3600
-
-# Enable third parties caching (e.g LangChain cache)
-cache = false
-
-# Authorized origins
-allow_origins = ["*"]
-
-# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
-# follow_symlink = false
-
-[features]
-# Show the prompt playground
-prompt_playground = true
-
-# Process and display HTML in messages. This can be a security risk (see https://stackoverflow.com/questions/19603097/why-is-it-dangerous-to-render-user-generated-html-or-javascript)
-unsafe_allow_html = false
-
-# Process and display mathematical expressions. This can clash with "$" characters in messages.
-latex = false
-
-# Automatically tag threads with the current chat profile (if a chat profile is used)
-auto_tag_thread = true
-
-# Authorize users to spontaneously upload files with messages
-[features.spontaneous_file_upload]
-    enabled = true
-    accept = ["*/*"]
-    max_files = 20
-    max_size_mb = 500
-
-[features.audio]
-    # Threshold for audio recording
-    min_decibels = -45
-    # Delay for the user to start speaking in MS
-    initial_silence_timeout = 3000
-    # Delay for the user to continue speaking in MS. If the user stops speaking for this duration, the recording will stop.
-    silence_timeout = 1500
-    # Above this duration (MS), the recording will forcefully stop.
-    max_duration = 15000
-    # Duration of the audio chunks in MS
-    chunk_duration = 1000
-    # Sample rate of the audio
-    sample_rate = 44100
-
-[UI]
-# Name of the app and chatbot.
-name = "Chatbot"
-
-# Show the readme while the thread is empty.
-show_readme_as_default = true
-
-# Description of the app and chatbot. This is used for HTML tags.
-# description = ""
-
-# Large size content are by default collapsed for a cleaner ui
-default_collapse_content = true
-
-# The default value for the expand messages settings.
-default_expand_messages = false
-
-# Hide the chain of thought details from the user in the UI.
-hide_cot = false
-
-# Link to your github repo. This will add a github button in the UI's header.
-# github = ""
-
-# Specify a CSS file that can be used to customize the user interface.
-# The CSS file can be served from the public directory or via an external link.
-# custom_css = "/public/test.css"
-
-# Specify a Javascript file that can be used to customize the user interface.
-# The Javascript file can be served from the public directory.
-# custom_js = "/public/test.js"
-
-# Specify a custom font url.
-# custom_font = "https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700&display=swap"
-
-# Specify a custom meta image url.
-# custom_meta_image_url = "https://chainlit-cloud.s3.eu-west-3.amazonaws.com/logo/chainlit_banner.png"
-
-# Specify a custom build directory for the frontend.
-# This can be used to customize the frontend code.
-# Be careful: If this is a relative path, it should not start with a slash.
-# custom_build = "./public/build"
-
-[UI.theme]
-    #layout = "wide"
-    #font_family = "Inter, sans-serif"
-# Override default MUI light theme. (Check theme.ts)
-[UI.theme.light]
-    #background = "#FAFAFA"
-    #paper = "#FFFFFF"
-
-    [UI.theme.light.primary]
-        #main = "#F80061"
-        #dark = "#980039"
-        #light = "#FFE7EB"
-
-# Override default MUI dark theme. (Check theme.ts)
-[UI.theme.dark]
-    #background = "#FAFAFA"
-    #paper = "#FFFFFF"
-
-    [UI.theme.dark.primary]
-        #main = "#F80061"
-        #dark = "#980039"
-        #light = "#FFE7EB"
-
-
-[meta]
-generated_by = "1.1.202"