langroid 0.32.1__py3-none-any.whl → 0.32.2__py3-none-any.whl

langroid/language_models/.chainlit/translations/en-US.json

@@ -1,231 +0,0 @@
-{
-    "components": {
-        "atoms": {
-            "buttons": {
-                "userButton": {
-                    "menu": {
-                        "settings": "Settings",
-                        "settingsKey": "S",
-                        "APIKeys": "API Keys",
-                        "logout": "Logout"
-                    }
-                }
-            }
-        },
-        "molecules": {
-            "newChatButton": {
-                "newChat": "New Chat"
-            },
-            "tasklist": {
-                "TaskList": {
-                    "title": "\ud83d\uddd2\ufe0f Task List",
-                    "loading": "Loading...",
-                    "error": "An error occured"
-                }
-            },
-            "attachments": {
-                "cancelUpload": "Cancel upload",
-                "removeAttachment": "Remove attachment"
-            },
-            "newChatDialog": {
-                "createNewChat": "Create new chat?",
-                "clearChat": "This will clear the current messages and start a new chat.",
-                "cancel": "Cancel",
-                "confirm": "Confirm"
-            },
-            "settingsModal": {
-                "settings": "Settings",
-                "expandMessages": "Expand Messages",
-                "hideChainOfThought": "Hide Chain of Thought",
-                "darkMode": "Dark Mode"
-            },
-            "detailsButton": {
-                "using": "Using",
-                "running": "Running",
-                "took_one": "Took {{count}} step",
-                "took_other": "Took {{count}} steps"
-            },
-            "auth": {
-                "authLogin": {
-                    "title": "Login to access the app.",
-                    "form": {
-                        "email": "Email address",
-                        "password": "Password",
-                        "noAccount": "Don't have an account?",
-                        "alreadyHaveAccount": "Already have an account?",
-                        "signup": "Sign Up",
-                        "signin": "Sign In",
-                        "or": "OR",
-                        "continue": "Continue",
-                        "forgotPassword": "Forgot password?",
-                        "passwordMustContain": "Your password must contain:",
-                        "emailRequired": "email is a required field",
-                        "passwordRequired": "password is a required field"
-                    },
-                    "error": {
-                        "default": "Unable to sign in.",
-                        "signin": "Try signing in with a different account.",
-                        "oauthsignin": "Try signing in with a different account.",
-                        "redirect_uri_mismatch": "The redirect URI is not matching the oauth app configuration.",
-                        "oauthcallbackerror": "Try signing in with a different account.",
-                        "oauthcreateaccount": "Try signing in with a different account.",
-                        "emailcreateaccount": "Try signing in with a different account.",
-                        "callback": "Try signing in with a different account.",
-                        "oauthaccountnotlinked": "To confirm your identity, sign in with the same account you used originally.",
-                        "emailsignin": "The e-mail could not be sent.",
-                        "emailverify": "Please verify your email, a new email has been sent.",
-                        "credentialssignin": "Sign in failed. Check the details you provided are correct.",
-                        "sessionrequired": "Please sign in to access this page."
-                    }
-                },
-                "authVerifyEmail": {
-                    "almostThere": "You're almost there! We've sent an email to ",
-                    "verifyEmailLink": "Please click on the link in that email to complete your signup.",
-                    "didNotReceive": "Can't find the email?",
-                    "resendEmail": "Resend email",
-                    "goBack": "Go Back",
-                    "emailSent": "Email sent successfully.",
-                    "verifyEmail": "Verify your email address"
-                },
-                "providerButton": {
-                    "continue": "Continue with {{provider}}",
-                    "signup": "Sign up with {{provider}}"
-                },
-                "authResetPassword": {
-                    "newPasswordRequired": "New password is a required field",
-                    "passwordsMustMatch": "Passwords must match",
-                    "confirmPasswordRequired": "Confirm password is a required field",
-                    "newPassword": "New password",
-                    "confirmPassword": "Confirm password",
-                    "resetPassword": "Reset Password"
-                },
-                "authForgotPassword": {
-                    "email": "Email address",
-                    "emailRequired": "email is a required field",
-                    "emailSent": "Please check the email address {{email}} for instructions to reset your password.",
-                    "enterEmail": "Enter your email address and we will send you instructions to reset your password.",
-                    "resendEmail": "Resend email",
-                    "continue": "Continue",
-                    "goBack": "Go Back"
-                }
-            }
-        },
-        "organisms": {
-            "chat": {
-                "history": {
-                    "index": {
-                        "showHistory": "Show history",
-                        "lastInputs": "Last Inputs",
-                        "noInputs": "Such empty...",
-                        "loading": "Loading..."
-                    }
-                },
-                "inputBox": {
-                    "input": {
-                        "placeholder": "Type your message here..."
-                    },
-                    "speechButton": {
-                        "start": "Start recording",
-                        "stop": "Stop recording"
-                    },
-                    "SubmitButton": {
-                        "sendMessage": "Send message",
-                        "stopTask": "Stop Task"
-                    },
-                    "UploadButton": {
-                        "attachFiles": "Attach files"
-                    },
-                    "waterMark": {
-                        "text": "Built with"
-                    }
-                },
-                "Messages": {
-                    "index": {
-                        "running": "Running",
-                        "executedSuccessfully": "executed successfully",
-                        "failed": "failed",
-                        "feedbackUpdated": "Feedback updated",
-                        "updating": "Updating"
-                    }
-                },
-                "dropScreen": {
-                    "dropYourFilesHere": "Drop your files here"
-                },
-                "index": {
-                    "failedToUpload": "Failed to upload",
-                    "cancelledUploadOf": "Cancelled upload of",
-                    "couldNotReachServer": "Could not reach the server",
-                    "continuingChat": "Continuing previous chat"
-                },
-                "settings": {
-                    "settingsPanel": "Settings panel",
-                    "reset": "Reset",
-                    "cancel": "Cancel",
-                    "confirm": "Confirm"
-                }
-            },
-            "threadHistory": {
-                "sidebar": {
-                    "filters": {
-                        "FeedbackSelect": {
-                            "feedbackAll": "Feedback: All",
-                            "feedbackPositive": "Feedback: Positive",
-                            "feedbackNegative": "Feedback: Negative"
-                        },
-                        "SearchBar": {
-                            "search": "Search"
-                        }
-                    },
-                    "DeleteThreadButton": {
-                        "confirmMessage": "This will delete the thread as well as it's messages and elements.",
-                        "cancel": "Cancel",
-                        "confirm": "Confirm",
-                        "deletingChat": "Deleting chat",
-                        "chatDeleted": "Chat deleted"
-                    },
-                    "index": {
-                        "pastChats": "Past Chats"
-                    },
-                    "ThreadList": {
-                        "empty": "Empty...",
-                        "today": "Today",
-                        "yesterday": "Yesterday",
-                        "previous7days": "Previous 7 days",
-                        "previous30days": "Previous 30 days"
-                    },
-                    "TriggerButton": {
-                        "closeSidebar": "Close sidebar",
-                        "openSidebar": "Open sidebar"
-                    }
-                },
-                "Thread": {
-                    "backToChat": "Go back to chat",
-                    "chatCreatedOn": "This chat was created on"
-                }
-            },
-            "header": {
-                "chat": "Chat",
-                "readme": "Readme"
-            }
-        }
-    },
-    "hooks": {
-        "useLLMProviders": {
-            "failedToFetchProviders": "Failed to fetch providers:"
-        }
-    },
-    "pages": {
-        "Design": {},
-        "Env": {
-            "savedSuccessfully": "Saved successfully",
-            "requiredApiKeys": "Required API Keys",
-            "requiredApiKeysInfo": "To use this app, the following API keys are required. The keys are stored on your device's local storage."
-        },
-        "Page": {
-            "notPartOfProject": "You are not part of this project."
-        },
-        "ResumeButton": {
-            "resumeChat": "Resume Chat"
-        }
-    }
-}

langroid/parsing/code-parsing.md

@@ -1,86 +0,0 @@
-To split Python code files into meaningful chunks, you can use the `tree-sitter` library, which is a parser generator tool and an incremental parsing library. It can be used to parse source code into an abstract syntax tree (AST) and extract meaningful code blocks from it. Here's how you can use `tree-sitter` to achieve this:
-
-1. Install the `tree-sitter` Python package:
-```python
-pip install tree-sitter
-```
-
-2. Install the `tree-sitter-python` language grammar:
-```bash
-git clone https://github.com/tree-sitter/tree-sitter-python
-```
-
-3. Use `tree-sitter` to parse Python code files and extract meaningful code
-   blocks:
-
-```python
-from tree_sitter import Language, Parser
-
-# Set the path to the tree-sitter-python language grammar
-TREE_SITTER_PYTHON_PATH = './tree-sitter-python'
-
-# Build the Python language
-Language.build_library(
-    'build/my-languages.so',
-    [TREE_SITTER_PYTHON_PATH]
-)
-
-PYTHON_LANGUAGE = Language('build/my-languages.so', 'python')
-
-# Create a parser
-parser = Parser()
-parser.set_language(PYTHON_LANGUAGE)
-
-# Parse the code
-code = """
-def foo():
-    return "Hello, World!"
-
-def bar():
-    return "Goodbye, World!"
-"""
-
-tree = parser.parse(bytes(code, 'utf8'))
-
-# Extract meaningful code blocks (e.g., function definitions)
-def extract_functions(node):
-    functions = []
-    for child in node.children:
-        if child.type == 'function_definition':
-            start_byte = child.start_byte
-            end_byte = child.end_byte
-            functions.append(code[start_byte:end_byte])
-        functions.extend(extract_functions(child))
-    return functions
-
-functions = extract_functions(tree.root_node)
-print(functions)
-```
-
-In the example provided, the `tree-sitter` library is used to parse the Python
-code into an abstract syntax tree (AST). The `extract_functions` function is
-then used to recursively traverse the AST and extract code blocks corresponding
-to function definitions. The extracted code blocks are stored in the `functions`
-list.
-
-The `extract_functions` function takes an AST node as input and returns a list
-of code blocks corresponding to function definitions. It checks whether the
-current node is of type `'function_definition'` (which corresponds to a function
-definition in Python code). If it is, the function extracts the corresponding
-code block from the original code using the `start_byte` and `end_byte`
-attributes of the node. The function then recursively processes the children of
-the current node to extract any nested function definitions.
-
-The resulting list `functions` contains the extracted code blocks, each
-representing a function definition from the original code. You can modify
-the `extract_functions` function to extract other types of code blocks (e.g.,
-class definitions, loops) by checking for different node types in the AST.
-
-Once you have extracted the code blocks, you can proceed with further
-processing, such as converting them into vectors and storing them in a vector
-database, as mentioned in the previous response.
-
-Note: The code provided in this response is a basic example to demonstrate the
-concept. Depending on your specific use case and requirements, you may need to
-extend or modify the code to handle more complex scenarios, such as handling
-comments, docstrings, and other code constructs.

langroid/parsing/image_text.py

@@ -1,32 +0,0 @@
-from typing import Union
-
-import pytesseract
-from pdf2image import convert_from_bytes, convert_from_path
-
-
-def pdf_image_to_text(input_data: Union[str, bytes]) -> str:
-    """
-    Converts a PDF that contains images to text using OCR.
-
-    Args:
-        input_data (Union[str, bytes]): The file path to the PDF or a bytes-like object
-            of the PDF content.
-
-    Returns:
-        str: The extracted text from the PDF.
-    """
-
-    # Check if the input is a file path (str) or bytes, and
-    # convert PDF to images accordingly
-    if isinstance(input_data, str):
-        images = convert_from_path(input_data)
-    elif isinstance(input_data, bytes):
-        images = convert_from_bytes(input_data)
-    else:
-        raise ValueError("input_data must be a file path (str) or bytes-like object")
-
-    text = ""
-    for image in images:
-        text += pytesseract.image_to_string(image)
-
-    return text

langroid/parsing/url_loader_cookies.py

@@ -1,73 +0,0 @@
-import logging
-from typing import List, no_type_check
-
-import trafilatura
-from playwright.sync_api import sync_playwright
-
-from langroid.mytypes import DocMetaData, Document
-
-logging.getLogger("trafilatura").setLevel(logging.ERROR)
-
-
-def accept_cookies_and_extract_content(url: str) -> str:
-    with sync_playwright() as playwright:
-        browser = playwright.chromium.launch(headless=True)
-        context = browser.new_context()
-        page = context.new_page()
-        page.goto(url)
-
-        # List of possible selectors or texts on the cookie consent buttons
-        possible_selectors = [
-            'text="Accept"',
-            'text="Agree"',
-            'text="OK"',
-            'text="Continue"',
-        ]
-
-        # Try to click each possible consent button
-        for selector in possible_selectors:
-            try:
-                page.click(selector)
-                print(f"Clicked {selector}")
-                break  # If click is successful, break out of the loop
-            except Exception:
-                print(f"Could not click {selector}")
-
-        # Extract and return the page's text content
-        content = page.content()
-
-        context.close()
-        browser.close()
-        content_str: str = content if isinstance(content, str) else ""
-        return content_str
-
-
-class URLLoader:
-    """
-    Load a list of URLs and extract the text content.
-    Alternative approaches could use `bs4` or `scrapy`.
-
-    TODO - this currently does not handle cookie dialogs,
-     i.e. if there is a cookie pop-up, most/all of the extracted
-     content could be cookie policy text.
-     We could use `playwright` to simulate a user clicking
-     the "accept" button on the cookie dialog.
-    """
-
-    def __init__(self, urls: List[str]):
-        self.urls = urls
-
-    @no_type_check
-    def load(self) -> List[Document]:
-        docs = []
-        # converted the input list to an internal format
-        for url in self.urls:
-            html_content = accept_cookies_and_extract_content(url)
-            text = trafilatura.extract(
-                html_content,
-                no_fallback=False,
-                favor_recall=True,
-            )
-            if text is not None and text != "":
-                docs.append(Document(content=text, metadata=DocMetaData(source=url)))
-        return docs

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/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"