langroid 0.1.139__py3-none-any.whl → 0.1.219__py3-none-any.whl

langroid/parsing/web_search.py

@@ -12,6 +12,7 @@ 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
 
@@ -77,3 +78,75 @@ def google_search(query: str, num_results: int = 5) -> List[WebSearchResult]:
         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

@@ -2,3 +2,10 @@ from . import dialog
 from . import prompts_config
 from . import templates
 from . import transforms
+
+__all__ = [
+    "dialog",
+    "prompts_config",
+    "templates",
+    "transforms",
+]

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

@@ -0,0 +1,68 @@
+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/prompts_config.py

@@ -2,4 +2,4 @@ from pydantic import BaseSettings
 
 
 class PromptsConfig(BaseSettings):
-    max_tokens: int = 1000
+    max_tokens: int = 1000  # for output; NOT USED ANYWHERE

langroid/utils/__init__.py

@@ -5,3 +5,13 @@ from . import logging
 from . import pydantic_utils
 from . import system
 from . import output
+
+__all__ = [
+    "configuration",
+    "globals",
+    "constants",
+    "logging",
+    "pydantic_utils",
+    "system",
+    "output",
+]

langroid/utils/algorithms/__init__.py

@@ -0,0 +1,3 @@
+from . import graph
+
+__all__ = ["graph"]

langroid/utils/configuration.py

@@ -17,7 +17,6 @@ class Settings(BaseSettings):
     cache_type: Literal["redis", "fakeredis", "momento"] = "redis"  # cache type
     interactive: bool = True  # interactive mode?
     gpt3_5: bool = True  # use GPT-3.5?
-    nofunc: bool = False  # use model without function_call? (i.e. gpt-4)
     chat_model: str = ""  # language model name, e.g. litellm/ollama/llama2
     quiet: bool = False  # quiet mode (i.e. suppress all output)?
     notebook: bool = False  # running in a notebook?

langroid/utils/constants.py

@@ -16,3 +16,7 @@ class Colors(BaseModel):
 USER_QUIT = ["q", "x", "quit", "exit", "bye"]
 NO_ANSWER = "DO-NOT-KNOW"
 DONE = "DONE"
+PASS = "__PASS__"
+PASS_TO = PASS + ":"
+SEND_TO = "SEND:"
+TOOL = "TOOL"

langroid/utils/logging.py

@@ -72,12 +72,9 @@ def setup_file_logger(
     propagate: bool = False,
 ) -> logging.Logger:
     os.makedirs(os.path.dirname(filename), exist_ok=True)
-    if not append:
-        if os.path.exists(filename):
-            os.remove(filename)
-
+    file_mode = "a" if append else "w"
     logger = setup_logger(name)
-    handler = logging.FileHandler(filename)
+    handler = logging.FileHandler(filename, mode=file_mode)
     handler.setLevel(logging.INFO)
     if log_format:
         formatter = logging.Formatter(

langroid/utils/output/__init__.py

@@ -1,8 +1,21 @@
-import langroid.utils.output.printing as printing
+from . import printing
 
-from langroid.utils.output.printing import (
+from .printing import (
     shorten_text,
     print_long_text,
     show_if_debug,
+    SuppressLoggerWarnings,
     PrintColored,
 )
+
+from .status import status
+
+__all__ = [
+    "printing",
+    "shorten_text",
+    "print_long_text",
+    "show_if_debug",
+    "SuppressLoggerWarnings",
+    "PrintColored",
+    "status",
+]

langroid/utils/output/status.py

@@ -0,0 +1,33 @@
+import logging
+from contextlib import AbstractContextManager, ExitStack
+from typing import Any
+
+from rich.console import Console
+
+from langroid.utils.configuration import quiet_mode, settings
+
+console = Console()
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+
+
+def status(
+    msg: str,
+    log_if_quiet: bool = True,
+) -> AbstractContextManager[Any]:
+    """
+    Displays a rich spinner if not in quiet mode, else optionally logs the message.
+    """
+    stack = ExitStack()
+
+    if settings.quiet:
+        if log_if_quiet:
+            logger.info(msg)
+    if settings.quiet and log_if_quiet:
+        logger.info(msg)
+    else:
+        stack.enter_context(console.status(msg))
+
+    stack.enter_context(quiet_mode(not settings.debug))
+
+    return stack

langroid/utils/pandas_utils.py

@@ -0,0 +1,30 @@
+from typing import Any
+
+import pandas as pd
+
+
+def stringify(x: Any) -> str:
+    # Convert x to DataFrame if it is not one already
+    if isinstance(x, pd.Series):
+        df = x.to_frame()
+    elif not isinstance(x, pd.DataFrame):
+        return str(x)
+    else:
+        df = x
+
+    # Truncate long text columns to 1000 characters
+    for col in df.columns:
+        if df[col].dtype == object:
+            df[col] = df[col].apply(
+                lambda item: (
+                    (item[:1000] + "...")
+                    if isinstance(item, str) and len(item) > 1000
+                    else item
+                )
+            )
+
+    # Limit to 10 rows
+    df = df.head(10)
+
+    # Convert to string
+    return df.to_string(index=False)  # type: ignore