langroid 0.1.22__tar.gz → 0.1.23__tar.gz

{langroid-0.1.22 → langroid-0.1.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.22
+Version: 0.1.23
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -61,61 +61,51 @@ Description-Content-Type: text/markdown
   <h1>Langroid: Harness LLMs with Multi-Agent Programming</h1>
 </div>
 
+<div align="center">
+
 [![Pytest](https://github.com/langroid/langroid/actions/workflows/pytest.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/pytest.yml)
 [![Lint](https://github.com/langroid/langroid/actions/workflows/validate.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/validate.yml)
 [![Docs](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml)
+[![Static Badge](https://img.shields.io/badge/Documentation-blue?link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F&link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F)](https://langroid.github.io/langroid)
+[![Static Badge](https://img.shields.io/badge/Discord-Orange?link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ&link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ)](https://discord.gg/g3nAXCbZ)
+
+</div>
 
 Langroid is an intuitive, lightweight, transparent, flexible, extensible and principled
-Python framework to harness LLMs using Multi-Agent Programming (MAP).
+Python framework to build LLM-powered applications using Multi-Agent Programming. 
 We welcome [contributions](CONTRIBUTING.md)!
 
+Langroid is the first Python LLM-application framework that was explicitly
+designed  with Agents as first-class citizens, and Multi-Agent Programming
+as the core  design principle. The framework is inspired by ideas from the
+[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).
+For more details see [here](https://langroid.github.io/langroid/).
+
 Documentation: https://langroid.github.io/langroid/
 
 Usage examples: https://github.com/langroid/langroid-examples
 
-## Overview
-
-### The LLM Opportunity
-
-Given the remarkable abilities of recent Large Language Models (LLMs), there
-is an unprecedented opportunity to build intelligent applications powered by
-this transformative technology. The top question for any enterprise is: how
-best to harness the power of LLMs for complex applications? For technical and
-practical reasons, building LLM-powered applications is not as simple as
-throwing a task at an LLM-system and expecting it to do it.
+Community: Join us on [Discord!](https://discord.gg/g3nAXCbZ)
 
-### Langroid's Multi-Agent Programming Framework
+## :rocket: Demo
 
-Effectively leveraging LLMs at scale requires a *principled programming
-framework*. In particular, there is often a need to maintain multiple LLM
-conversations, each instructed in different ways, and "responsible" for
-different aspects of a task.
+A `LeaseExtractor` agent is tasked with extracting structured information
+from a commercial lease document. It generates questions that are 
+answerred by a `DocAgent` using Retrieval from a vector-database
+(into which the lease has been sharded + embedded).
+When it has all the information it needs, the `LeaseExtractor` agent
+presents the information in a structured format using a Tool/Function-calling.
 
-An *agent* is a convenient abstraction that encapsulates LLM conversation
-state, along with access to long-term memory (vector-stores) and tools (a.k.a functions
-or plugins). Thus a **Multi-Agent Programming** framework is a natural fit
-for complex LLM-based applications.
+![Demo](lease-extractor-demo.gif)
 
-> Langroid is the first Python LLM-application framework that was explicitly
-designed  with Agents as first-class citizens, and Multi-Agent Programming
-as the core  design principle. The framework is inspired by ideas from the
-[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).
 
-Langroid allows an intuitive definition of agents, tasks and task-delegation
-among agents. There is a principled mechanism to orchestrate multi-agent
-collaboration. Agents act as message-transformers, and take turns responding to (and
-transforming) the current message. The architecture is lightweight, transparent,
-flexible, and allows other types of orchestration to be implemented.
-Besides Agents, Langroid also provides simple ways to directly interact with  
-LLMs and vector-stores.
+## :zap: Highlights
 
-### Highlights
 Highlights of Langroid's features as of July 2023:
 
 - **Agents as first-class citizens:** The `Agent` class encapsulates LLM conversation state,
   and optionally a vector-store and tools. Agents are a core abstraction in Langroid;
-  Agents act as _message transformers_, and by default provide 3 _responder_ methods,  
-  one corresponding to each entity: LLM, Agent, User.
+  Agents act as _message transformers_, and by default provide 3 _responder_ methods, one corresponding to each entity: LLM, Agent, User.
 - **Tasks:** A Task class wraps an Agent, and gives the agent instructions (or roles, or goals), 
   manages iteration over an Agent's responder methods, 
   and orchestrates multi-agent interactions via hierarchical, recursive
@@ -130,7 +120,7 @@ Highlights of Langroid's features as of July 2023:
   GPT-4-0613
 - **Caching of LLM prompts, responses:** Langroid uses [Redis](https://redis.com/try-free/) for caching.
 - **Vector-stores**: [Qdrant](https://qdrant.tech/) and [Chroma](https://www.trychroma.com/) are currently supported.
-  Vector stores allow for Retrieval-Augmented-Generaation (RAG).
+  Vector stores allow for Retrieval-Augmented-Generation (RAG).
 - **Grounding and source-citation:** Access to external documents via vector-stores 
    allows for grounding and source-citation.
 - **Observability, Logging, Lineage:** Langroid generates detailed logs of multi-agent interactions and
@@ -148,11 +138,9 @@ Highlights of Langroid's features as of July 2023:
   hallucinates malformed JSON, the Pydantic error message is sent back to
   the LLM so it can fix it!
 
-# Usage/quick-start
-These are quick teasers to give a glimpse of what you can do with Langroid
-and how your code would look. See the 
-[`Getting Started Guide`](https://langroid.github.io/langroid/getting_started/)
-for a detailed tutorial.
+--- 
+
+# :gear: Installation and Setup
 
 ## Install `langroid` 
 Use `pip` to install `langroid` (from PyPi) to your virtual environment:
@@ -173,7 +161,7 @@ Copy the `.env-template` file to a new file `.env` and
 insert these secrets:
 - **OpenAI API** key (required): If you don't have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).
 - **Qdrant** Vector Store API Key (required for apps that need retrieval from
-  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io)
+  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io).
   Alternatively [Chroma](https://docs.trychroma.com/) is also currently supported. 
   We use the local-storage version of Chroma, so there is no need for an API key.
 - **GitHub** Personal Access Token (required for apps that need to analyze git
@@ -198,7 +186,32 @@ QDRANT_API_KEY=<your key>
 Currently only OpenAI models are supported. Others will be added later
 (Pull Requests welcome!).
 
-## Direct interaction with OpenAI LLM
+---
+
+# :tada: Usage Examples
+
+These are quick teasers to give a glimpse of what you can do with Langroid
+and how your code would look. 
+
+:warning: The code snippets below are intended to give a flavor of the code
+and they are **not** complete runnable examples! For that we encourage you to 
+consult the [`langroid-examples`](https://github.com/langroid/langroid-examples) 
+repository.
+
+Also see the
+[`Getting Started Guide`](https://langroid.github.io/langroid/quick-start/)
+for a detailed tutorial. 
+
+- [Direct chat with LLM](#direct-llm)
+- [Simple Agent and Task](#agent-task)
+- [Three Communicating Agents](#three-agents)
+- [Agent with Tool/Function-calling](#agent-tool)
+- [Extract Structured Info with Tool/Function-calling](#agent-tool-structured)
+- [Retrieval-Augmented-Generation: Chat with Docs](#agent-rag)
+
+---
+
+## Direct interaction with OpenAI LLM <a name="direct-llm"></a>
 
 ```python
 from langroid.language_models.openai_gpt import ( 
@@ -213,11 +226,14 @@ mdl = OpenAIGPT(cfg)
 messages = [
   LLMMessage(content="You are a helpful assistant",  role=Role.SYSTEM), 
   LLMMessage(content="What is the capital of Ontario?",  role=Role.USER),
-],
+]
 response = mdl.chat(messages, max_tokens=200)
+print(response.message)
 ```
 
-## Define an agent, set up a task, and run it
+---
+
+## Define an agent, set up a task, and run it <a name="agent-task"></a>
 
 ```python
 from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
@@ -232,13 +248,15 @@ config = ChatAgentConfig(
 )
 agent = ChatAgent(config)
 # get response from agent's LLM, and put this in an interactive loop...
-answer = agent.llm_response("What is the capital of Ontario?")
-# ... or set up a task (which has a built-in loop) and run it
+# answer = agent.llm_response("What is the capital of Ontario?")
+  # ... OR instead, set up a task (which has a built-in loop) and run it
 task = Task(agent, name="Bot") 
-task.run() # ... a loop seeking response from Agent, LLM or User at each turn
+task.run() # ... a loop seeking response from LLM or User at each turn
 ```
 
-## Three communicating agents
+---
+
+## Three communicating agents <a name="three-agents"></a>
 
 A toy numbers game, where when given a number `n`:
 - `repeater_agent`'s LLM simply returns `n`,
@@ -248,57 +266,66 @@ A toy numbers game, where when given a number `n`:
 First define the 3 agents, and set up their tasks with instructions:
 
 ```python
-    config = ChatAgentConfig(
-        llm = OpenAIGPTConfig(
-            chat_model=OpenAIChatModel.GPT4,
-        ),
-        vecdb = None,
-    )
-    repeater_agent = ChatAgent(config)
-    repeater_task = Task(
-        repeater_agent,
-        name = "Repeater",
-        system_message="""
-        Your job is to repeat whatever number you receive.
-        """,
-        llm_delegate=True, # LLM takes charge of task
-        single_round=False, 
-    )
-    even_agent = ChatAgent(config)
-    even_task = Task(
-        even_agent,
-        name = "EvenHandler",
-        system_message=f"""
-        You will be given a number. 
-        If it is even, divide by 2 and say the result, nothing else.
-        If it is odd, say {NO_ANSWER}
-        """,
-        single_round=True,  # task done after 1 step() with valid response
-    )
+from langroid.utils.constants import NO_ANSWER
+from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
+from langroid.agent.task import Task
+from langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig
+config = ChatAgentConfig(
+    llm = OpenAIGPTConfig(
+        chat_model=OpenAIChatModel.GPT4,
+    ),
+    vecdb = None,
+)
+repeater_agent = ChatAgent(config)
+repeater_task = Task(
+    repeater_agent,
+    name = "Repeater",
+    system_message="""
+    Your job is to repeat whatever number you receive.
+    """,
+    llm_delegate=True, # LLM takes charge of task
+    single_round=False, 
+)
+even_agent = ChatAgent(config)
+even_task = Task(
+    even_agent,
+    name = "EvenHandler",
+    system_message=f"""
+    You will be given a number. 
+    If it is even, divide by 2 and say the result, nothing else.
+    If it is odd, say {NO_ANSWER}
+    """,
+    single_round=True,  # task done after 1 step() with valid response
+)
 
-    odd_agent = ChatAgent(config)
-    odd_task = Task(
-        odd_agent,
-        name = "OddHandler",
-        system_message=f"""
-        You will be given a number n. 
-        If it is odd, return (n*3+1), say nothing else. 
-        If it is even, say {NO_ANSWER}
-        """,
-        single_round=True,  # task done after 1 step() with valid response
-    )
+odd_agent = ChatAgent(config)
+odd_task = Task(
+    odd_agent,
+    name = "OddHandler",
+    system_message=f"""
+    You will be given a number n. 
+    If it is odd, return (n*3+1), say nothing else. 
+    If it is even, say {NO_ANSWER}
+    """,
+    single_round=True,  # task done after 1 step() with valid response
+)
 ```
 Then add the `even_task` and `odd_task` as sub-tasks of `repeater_task`, 
 and run the `repeater_task`, kicking it off with a number as input:
 ```python
-    repeater_task.add_sub_task([even_task, odd_task])
-    repeater_task.run("3")
+repeater_task.add_sub_task([even_task, odd_task])
+repeater_task.run("3")
 ```
+---
+
+## Simple Tool/Function-calling example <a name="agent-tool"></a>
 
-### Simple Tool/Function-calling example
 Langroid leverages Pydantic to support OpenAI's
 [Function-calling API](https://platform.openai.com/docs/guides/gpt/function-calling)
-as well as its own native tools.
+as well as its own native tools. The benefits are that you don't have to write
+any JSON to specify the schema, and also if the LLM hallucinates a malformed
+tool syntax, Langroid sends the Pydantic validation error (suitiably sanitized) 
+to the LLM so it can fix it!
 
 Simple example: Say the agent has a secret list of numbers, 
 and we want the LLM to find the smallest number in the list. 
@@ -357,7 +384,9 @@ For a full working example see the
 [chat-agent-tool.py](https://github.com/langroid/langroid-examples/blob/main/examples/quick-start/chat-agent-tool.py)
 script in the `langroid-examples` repo.
 
-### Tool/Function-calling to extract structured information from text
+---
+
+## Tool/Function-calling to extract structured information from text <a name="agent-tool-structured"></a>
 
 Suppose you want an agent to extract 
 the key terms of a lease, from a lease document, as a nested JSON structure.
@@ -381,7 +410,7 @@ class Lease(BaseModel):
 ```
 
 Then define the `LeaseMessage` tool as a subclass of Langroid's `ToolMessage`.
-Note the tool as a required argument `terms` of type `Lease`:
+Note the tool has a required argument `terms` of type `Lease`:
 
 ```python
 class LeaseMessage(ToolMessage):
@@ -419,8 +448,9 @@ lease_extractor_agent.enable_message(LeaseMessage)
 See the [`chat_multi_extract.py`](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py)
 script in the `langroid-examples` repo for a full working example.
 
+---
 
-### Chat with documents (file paths, URLs, etc)
+## Chat with documents (file paths, URLs, etc) <a name="agent-docs"></a>
 
 Langroid provides a specialized agent class `DocChatAgent` for this purpose.
 It incorporates document sharding, embedding, storage in a vector-DB, 
@@ -467,8 +497,9 @@ See full working scripts in the
 [`docqa`](https://github.com/langroid/langroid-examples/tree/main/examples/docqa)
 folder of the `langroid-examples` repo.
 
+---
 
-## Contributors
+# Contributors
 
 - Prasad Chalasani (IIT BTech/CS, CMU PhD/ML; Independent ML Consultant)
 - Somesh Jha (IIT BTech/CS, CMU PhD/CS; Professor of CS, U Wisc at Madison)

{langroid-0.1.22 → langroid-0.1.23}/README.md

@@ -4,61 +4,51 @@
   <h1>Langroid: Harness LLMs with Multi-Agent Programming</h1>
 </div>
 
+<div align="center">
+
 [![Pytest](https://github.com/langroid/langroid/actions/workflows/pytest.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/pytest.yml)
 [![Lint](https://github.com/langroid/langroid/actions/workflows/validate.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/validate.yml)
 [![Docs](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml)
+[![Static Badge](https://img.shields.io/badge/Documentation-blue?link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F&link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F)](https://langroid.github.io/langroid)
+[![Static Badge](https://img.shields.io/badge/Discord-Orange?link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ&link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ)](https://discord.gg/g3nAXCbZ)
+
+</div>
 
 Langroid is an intuitive, lightweight, transparent, flexible, extensible and principled
-Python framework to harness LLMs using Multi-Agent Programming (MAP).
+Python framework to build LLM-powered applications using Multi-Agent Programming. 
 We welcome [contributions](CONTRIBUTING.md)!
 
+Langroid is the first Python LLM-application framework that was explicitly
+designed  with Agents as first-class citizens, and Multi-Agent Programming
+as the core  design principle. The framework is inspired by ideas from the
+[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).
+For more details see [here](https://langroid.github.io/langroid/).
+
 Documentation: https://langroid.github.io/langroid/
 
 Usage examples: https://github.com/langroid/langroid-examples
 
-## Overview
-
-### The LLM Opportunity
-
-Given the remarkable abilities of recent Large Language Models (LLMs), there
-is an unprecedented opportunity to build intelligent applications powered by
-this transformative technology. The top question for any enterprise is: how
-best to harness the power of LLMs for complex applications? For technical and
-practical reasons, building LLM-powered applications is not as simple as
-throwing a task at an LLM-system and expecting it to do it.
+Community: Join us on [Discord!](https://discord.gg/g3nAXCbZ)
 
-### Langroid's Multi-Agent Programming Framework
+## :rocket: Demo
 
-Effectively leveraging LLMs at scale requires a *principled programming
-framework*. In particular, there is often a need to maintain multiple LLM
-conversations, each instructed in different ways, and "responsible" for
-different aspects of a task.
+A `LeaseExtractor` agent is tasked with extracting structured information
+from a commercial lease document. It generates questions that are 
+answerred by a `DocAgent` using Retrieval from a vector-database
+(into which the lease has been sharded + embedded).
+When it has all the information it needs, the `LeaseExtractor` agent
+presents the information in a structured format using a Tool/Function-calling.
 
-An *agent* is a convenient abstraction that encapsulates LLM conversation
-state, along with access to long-term memory (vector-stores) and tools (a.k.a functions
-or plugins). Thus a **Multi-Agent Programming** framework is a natural fit
-for complex LLM-based applications.
+![Demo](lease-extractor-demo.gif)
 
-> Langroid is the first Python LLM-application framework that was explicitly
-designed  with Agents as first-class citizens, and Multi-Agent Programming
-as the core  design principle. The framework is inspired by ideas from the
-[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).
 
-Langroid allows an intuitive definition of agents, tasks and task-delegation
-among agents. There is a principled mechanism to orchestrate multi-agent
-collaboration. Agents act as message-transformers, and take turns responding to (and
-transforming) the current message. The architecture is lightweight, transparent,
-flexible, and allows other types of orchestration to be implemented.
-Besides Agents, Langroid also provides simple ways to directly interact with  
-LLMs and vector-stores.
+## :zap: Highlights
 
-### Highlights
 Highlights of Langroid's features as of July 2023:
 
 - **Agents as first-class citizens:** The `Agent` class encapsulates LLM conversation state,
   and optionally a vector-store and tools. Agents are a core abstraction in Langroid;
-  Agents act as _message transformers_, and by default provide 3 _responder_ methods,  
-  one corresponding to each entity: LLM, Agent, User.
+  Agents act as _message transformers_, and by default provide 3 _responder_ methods, one corresponding to each entity: LLM, Agent, User.
 - **Tasks:** A Task class wraps an Agent, and gives the agent instructions (or roles, or goals), 
   manages iteration over an Agent's responder methods, 
   and orchestrates multi-agent interactions via hierarchical, recursive
@@ -73,7 +63,7 @@ Highlights of Langroid's features as of July 2023:
   GPT-4-0613
 - **Caching of LLM prompts, responses:** Langroid uses [Redis](https://redis.com/try-free/) for caching.
 - **Vector-stores**: [Qdrant](https://qdrant.tech/) and [Chroma](https://www.trychroma.com/) are currently supported.
-  Vector stores allow for Retrieval-Augmented-Generaation (RAG).
+  Vector stores allow for Retrieval-Augmented-Generation (RAG).
 - **Grounding and source-citation:** Access to external documents via vector-stores 
    allows for grounding and source-citation.
 - **Observability, Logging, Lineage:** Langroid generates detailed logs of multi-agent interactions and
@@ -91,11 +81,9 @@ Highlights of Langroid's features as of July 2023:
   hallucinates malformed JSON, the Pydantic error message is sent back to
   the LLM so it can fix it!
 
-# Usage/quick-start
-These are quick teasers to give a glimpse of what you can do with Langroid
-and how your code would look. See the 
-[`Getting Started Guide`](https://langroid.github.io/langroid/getting_started/)
-for a detailed tutorial.
+--- 
+
+# :gear: Installation and Setup
 
 ## Install `langroid` 
 Use `pip` to install `langroid` (from PyPi) to your virtual environment:
@@ -116,7 +104,7 @@ Copy the `.env-template` file to a new file `.env` and
 insert these secrets:
 - **OpenAI API** key (required): If you don't have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).
 - **Qdrant** Vector Store API Key (required for apps that need retrieval from
-  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io)
+  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io).
   Alternatively [Chroma](https://docs.trychroma.com/) is also currently supported. 
   We use the local-storage version of Chroma, so there is no need for an API key.
 - **GitHub** Personal Access Token (required for apps that need to analyze git
@@ -141,7 +129,32 @@ QDRANT_API_KEY=<your key>
 Currently only OpenAI models are supported. Others will be added later
 (Pull Requests welcome!).
 
-## Direct interaction with OpenAI LLM
+---
+
+# :tada: Usage Examples
+
+These are quick teasers to give a glimpse of what you can do with Langroid
+and how your code would look. 
+
+:warning: The code snippets below are intended to give a flavor of the code
+and they are **not** complete runnable examples! For that we encourage you to 
+consult the [`langroid-examples`](https://github.com/langroid/langroid-examples) 
+repository.
+
+Also see the
+[`Getting Started Guide`](https://langroid.github.io/langroid/quick-start/)
+for a detailed tutorial. 
+
+- [Direct chat with LLM](#direct-llm)
+- [Simple Agent and Task](#agent-task)
+- [Three Communicating Agents](#three-agents)
+- [Agent with Tool/Function-calling](#agent-tool)
+- [Extract Structured Info with Tool/Function-calling](#agent-tool-structured)
+- [Retrieval-Augmented-Generation: Chat with Docs](#agent-rag)
+
+---
+
+## Direct interaction with OpenAI LLM <a name="direct-llm"></a>
 
 ```python
 from langroid.language_models.openai_gpt import ( 
@@ -156,11 +169,14 @@ mdl = OpenAIGPT(cfg)
 messages = [
   LLMMessage(content="You are a helpful assistant",  role=Role.SYSTEM), 
   LLMMessage(content="What is the capital of Ontario?",  role=Role.USER),
-],
+]
 response = mdl.chat(messages, max_tokens=200)
+print(response.message)
 ```
 
-## Define an agent, set up a task, and run it
+---
+
+## Define an agent, set up a task, and run it <a name="agent-task"></a>
 
 ```python
 from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
@@ -175,13 +191,15 @@ config = ChatAgentConfig(
 )
 agent = ChatAgent(config)
 # get response from agent's LLM, and put this in an interactive loop...
-answer = agent.llm_response("What is the capital of Ontario?")
-# ... or set up a task (which has a built-in loop) and run it
+# answer = agent.llm_response("What is the capital of Ontario?")
+  # ... OR instead, set up a task (which has a built-in loop) and run it
 task = Task(agent, name="Bot") 
-task.run() # ... a loop seeking response from Agent, LLM or User at each turn
+task.run() # ... a loop seeking response from LLM or User at each turn
 ```
 
-## Three communicating agents
+---
+
+## Three communicating agents <a name="three-agents"></a>
 
 A toy numbers game, where when given a number `n`:
 - `repeater_agent`'s LLM simply returns `n`,
@@ -191,57 +209,66 @@ A toy numbers game, where when given a number `n`:
 First define the 3 agents, and set up their tasks with instructions:
 
 ```python
-    config = ChatAgentConfig(
-        llm = OpenAIGPTConfig(
-            chat_model=OpenAIChatModel.GPT4,
-        ),
-        vecdb = None,
-    )
-    repeater_agent = ChatAgent(config)
-    repeater_task = Task(
-        repeater_agent,
-        name = "Repeater",
-        system_message="""
-        Your job is to repeat whatever number you receive.
-        """,
-        llm_delegate=True, # LLM takes charge of task
-        single_round=False, 
-    )
-    even_agent = ChatAgent(config)
-    even_task = Task(
-        even_agent,
-        name = "EvenHandler",
-        system_message=f"""
-        You will be given a number. 
-        If it is even, divide by 2 and say the result, nothing else.
-        If it is odd, say {NO_ANSWER}
-        """,
-        single_round=True,  # task done after 1 step() with valid response
-    )
+from langroid.utils.constants import NO_ANSWER
+from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
+from langroid.agent.task import Task
+from langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig
+config = ChatAgentConfig(
+    llm = OpenAIGPTConfig(
+        chat_model=OpenAIChatModel.GPT4,
+    ),
+    vecdb = None,
+)
+repeater_agent = ChatAgent(config)
+repeater_task = Task(
+    repeater_agent,
+    name = "Repeater",
+    system_message="""
+    Your job is to repeat whatever number you receive.
+    """,
+    llm_delegate=True, # LLM takes charge of task
+    single_round=False, 
+)
+even_agent = ChatAgent(config)
+even_task = Task(
+    even_agent,
+    name = "EvenHandler",
+    system_message=f"""
+    You will be given a number. 
+    If it is even, divide by 2 and say the result, nothing else.
+    If it is odd, say {NO_ANSWER}
+    """,
+    single_round=True,  # task done after 1 step() with valid response
+)
 
-    odd_agent = ChatAgent(config)
-    odd_task = Task(
-        odd_agent,
-        name = "OddHandler",
-        system_message=f"""
-        You will be given a number n. 
-        If it is odd, return (n*3+1), say nothing else. 
-        If it is even, say {NO_ANSWER}
-        """,
-        single_round=True,  # task done after 1 step() with valid response
-    )
+odd_agent = ChatAgent(config)
+odd_task = Task(
+    odd_agent,
+    name = "OddHandler",
+    system_message=f"""
+    You will be given a number n. 
+    If it is odd, return (n*3+1), say nothing else. 
+    If it is even, say {NO_ANSWER}
+    """,
+    single_round=True,  # task done after 1 step() with valid response
+)
 ```
 Then add the `even_task` and `odd_task` as sub-tasks of `repeater_task`, 
 and run the `repeater_task`, kicking it off with a number as input:
 ```python
-    repeater_task.add_sub_task([even_task, odd_task])
-    repeater_task.run("3")
+repeater_task.add_sub_task([even_task, odd_task])
+repeater_task.run("3")
 ```
+---
+
+## Simple Tool/Function-calling example <a name="agent-tool"></a>
 
-### Simple Tool/Function-calling example
 Langroid leverages Pydantic to support OpenAI's
 [Function-calling API](https://platform.openai.com/docs/guides/gpt/function-calling)
-as well as its own native tools.
+as well as its own native tools. The benefits are that you don't have to write
+any JSON to specify the schema, and also if the LLM hallucinates a malformed
+tool syntax, Langroid sends the Pydantic validation error (suitiably sanitized) 
+to the LLM so it can fix it!
 
 Simple example: Say the agent has a secret list of numbers, 
 and we want the LLM to find the smallest number in the list. 
@@ -300,7 +327,9 @@ For a full working example see the
 [chat-agent-tool.py](https://github.com/langroid/langroid-examples/blob/main/examples/quick-start/chat-agent-tool.py)
 script in the `langroid-examples` repo.
 
-### Tool/Function-calling to extract structured information from text
+---
+
+## Tool/Function-calling to extract structured information from text <a name="agent-tool-structured"></a>
 
 Suppose you want an agent to extract 
 the key terms of a lease, from a lease document, as a nested JSON structure.
@@ -324,7 +353,7 @@ class Lease(BaseModel):
 ```
 
 Then define the `LeaseMessage` tool as a subclass of Langroid's `ToolMessage`.
-Note the tool as a required argument `terms` of type `Lease`:
+Note the tool has a required argument `terms` of type `Lease`:
 
 ```python
 class LeaseMessage(ToolMessage):
@@ -362,8 +391,9 @@ lease_extractor_agent.enable_message(LeaseMessage)
 See the [`chat_multi_extract.py`](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py)
 script in the `langroid-examples` repo for a full working example.
 
+---
 
-### Chat with documents (file paths, URLs, etc)
+## Chat with documents (file paths, URLs, etc) <a name="agent-docs"></a>
 
 Langroid provides a specialized agent class `DocChatAgent` for this purpose.
 It incorporates document sharding, embedding, storage in a vector-DB, 
@@ -410,8 +440,9 @@ See full working scripts in the
 [`docqa`](https://github.com/langroid/langroid-examples/tree/main/examples/docqa)
 folder of the `langroid-examples` repo.
 
+---
 
-## Contributors
+# Contributors
 
 - Prasad Chalasani (IIT BTech/CS, CMU PhD/ML; Independent ML Consultant)
 - Somesh Jha (IIT BTech/CS, CMU PhD/CS; Professor of CS, U Wisc at Madison)

{langroid-0.1.22 → langroid-0.1.23}/langroid/agent/special/doc_chat_agent.py

@@ -324,7 +324,7 @@ class DocChatAgent(ChatAgent):
 
         passages = self.original_docs
 
-        # if original docs not too long, no need to look for relevant parts.
+        # if original docs too long, no need to look for relevant parts.
         if (
             passages is None
             or self.original_docs_length > self.config.max_context_tokens
@@ -380,8 +380,13 @@ class DocChatAgent(ChatAgent):
         if self.parser is None:
             raise ValueError("No parser defined")
         tot_tokens = self.parser.num_tokens(full_text)
+        model = (
+            self.config.llm.chat_model
+            if self.config.llm.use_chat_for_completion
+            else self.config.llm.completion_model
+        )
         MAX_INPUT_TOKENS = (
-            self.config.llm.context_length[self.config.llm.completion_model]
+            self.config.llm.context_length[model]
             - self.config.llm.max_output_tokens
             - 100
         )

{langroid-0.1.22 → langroid-0.1.23}/langroid/agent/task.py

@@ -1,8 +1,3 @@
-"""
-Class that runs the Task loop of an agent;
-maintains state while various responders (agent's own methods, or external sub-tasks)
-take turns attempting to respond to the `self.pending_message`.
-"""
 from __future__ import annotations
 
 import logging

{langroid-0.1.22 → langroid-0.1.23}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.1.22"
+version = "0.1.23"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"

langroid-0.1.23/setup.py

@@ -0,0 +1,85 @@
+# -*- coding: utf-8 -*-
+from setuptools import setup
+
+packages = \
+['langroid',
+ 'langroid.agent',
+ 'langroid.agent.special',
+ 'langroid.cachedb',
+ 'langroid.embedding_models',
+ 'langroid.language_models',
+ 'langroid.parsing',
+ 'langroid.prompts',
+ 'langroid.scripts',
+ 'langroid.utils',
+ 'langroid.utils.llms',
+ 'langroid.utils.output',
+ 'langroid.utils.web',
+ 'langroid.vector_store']
+
+package_data = \
+{'': ['*']}
+
+install_requires = \
+['autopep8>=2.0.2,<3.0.0',
+ 'black[jupyter]>=23.3.0,<24.0.0',
+ 'bs4>=0.0.1,<0.0.2',
+ 'chromadb>=0.3.21,<0.4.0',
+ 'colorlog>=6.7.0,<7.0.0',
+ 'faker>=18.9.0,<19.0.0',
+ 'fakeredis>=2.12.1,<3.0.0',
+ 'fire>=0.5.0,<0.6.0',
+ 'flake8>=6.0.0,<7.0.0',
+ 'halo>=0.0.31,<0.0.32',
+ 'mkdocs-awesome-pages-plugin>=2.8.0,<3.0.0',
+ 'mkdocs-gen-files>=0.4.0,<0.5.0',
+ 'mkdocs-jupyter>=0.24.1,<0.25.0',
+ 'mkdocs-literate-nav>=0.6.0,<0.7.0',
+ 'mkdocs-material>=9.1.5,<10.0.0',
+ 'mkdocs-section-index>=0.3.5,<0.4.0',
+ 'mkdocs>=1.4.2,<2.0.0',
+ 'mkdocstrings[python]>=0.21.2,<0.22.0',
+ 'mypy>=1.2.0,<2.0.0',
+ 'nltk>=3.8.1,<4.0.0',
+ 'openai>=0.27.5,<0.28.0',
+ 'pre-commit>=3.3.2,<4.0.0',
+ 'pydantic==1.10.11',
+ 'pygithub>=1.58.1,<2.0.0',
+ 'pygments>=2.15.1,<3.0.0',
+ 'pyparsing>=3.0.9,<4.0.0',
+ 'python-dotenv>=1.0.0,<2.0.0',
+ 'qdrant-client>=1.3.1,<2.0.0',
+ 'redis>=4.5.5,<5.0.0',
+ 'requests-oauthlib>=1.3.1,<2.0.0',
+ 'requests>=2.31.0,<3.0.0',
+ 'rich>=13.3.4,<14.0.0',
+ 'ruff>=0.0.270,<0.0.271',
+ 'tiktoken>=0.3.3,<0.4.0',
+ 'trafilatura>=1.5.0,<2.0.0',
+ 'typer>=0.7.0,<0.8.0',
+ 'types-redis>=4.5.5.2,<5.0.0.0',
+ 'types-requests>=2.31.0.1,<3.0.0.0',
+ 'wget>=3.2,<4.0']
+
+extras_require = \
+{'hf-embeddings': ['sentence-transformers==2.2.2', 'torch==2.0.0']}
+
+setup_kwargs = {
+    'name': 'langroid',
+    'version': '0.1.23',
+    'description': 'Harness LLMs with Multi-Agent Programming',
+    'long_description': '<div style="display: flex; align-items: center;">\n  <img src="docs/assets/orange-logo.png" alt="Logo" \n        width="80" height="80"align="left">\n  <h1>Langroid: Harness LLMs with Multi-Agent Programming</h1>\n</div>\n\n<div align="center">\n\n[![Pytest](https://github.com/langroid/langroid/actions/workflows/pytest.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/pytest.yml)\n[![Lint](https://github.com/langroid/langroid/actions/workflows/validate.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/validate.yml)\n[![Docs](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml)\n[![Static Badge](https://img.shields.io/badge/Documentation-blue?link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F&link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F)](https://langroid.github.io/langroid)\n[![Static Badge](https://img.shields.io/badge/Discord-Orange?link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ&link=https%3A%2F%2Fdiscord.gg%2Fg3nAXCbZ)](https://discord.gg/g3nAXCbZ)\n\n</div>\n\nLangroid is an intuitive, lightweight, transparent, flexible, extensible and principled\nPython framework to build LLM-powered applications using Multi-Agent Programming. \nWe welcome [contributions](CONTRIBUTING.md)!\n\nLangroid is the first Python LLM-application framework that was explicitly\ndesigned  with Agents as first-class citizens, and Multi-Agent Programming\nas the core  design principle. The framework is inspired by ideas from the\n[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).\nFor more details see [here](https://langroid.github.io/langroid/).\n\nDocumentation: https://langroid.github.io/langroid/\n\nUsage examples: https://github.com/langroid/langroid-examples\n\nCommunity: Join us on [Discord!](https://discord.gg/g3nAXCbZ)\n\n## :rocket: Demo\n\nA `LeaseExtractor` agent is tasked with extracting structured information\nfrom a commercial lease document. It generates questions that are \nanswerred by a `DocAgent` using Retrieval from a vector-database\n(into which the lease has been sharded + embedded).\nWhen it has all the information it needs, the `LeaseExtractor` agent\npresents the information in a structured format using a Tool/Function-calling.\n\n![Demo](lease-extractor-demo.gif)\n\n\n## :zap: Highlights\n\nHighlights of Langroid\'s features as of July 2023:\n\n- **Agents as first-class citizens:** The `Agent` class encapsulates LLM conversation state,\n  and optionally a vector-store and tools. Agents are a core abstraction in Langroid;\n  Agents act as _message transformers_, and by default provide 3 _responder_ methods, one corresponding to each entity: LLM, Agent, User.\n- **Tasks:** A Task class wraps an Agent, and gives the agent instructions (or roles, or goals), \n  manages iteration over an Agent\'s responder methods, \n  and orchestrates multi-agent interactions via hierarchical, recursive\n  task-delegation. The `Task.run()` method has the same \n  type-signature as an Agent\'s responder\'s methods, and this is key to how \n  a task of an agent can delegate to other sub-tasks: from the point of view of a Task,\n  sub-tasks are simply additional responders, to be used in a round-robin fashion \n  after the agent\'s own responders.\n- **Modularity, Reusabilily, Loose coupling:** The `Agent` and `Task` abstractions allow users to design\n  Agents with specific skills, wrap them in Tasks, and combine tasks in a flexible way.\n- **LLM Support**: Langroid supports OpenAI LLMs including GPT-3.5-Turbo,\n  GPT-4-0613\n- **Caching of LLM prompts, responses:** Langroid uses [Redis](https://redis.com/try-free/) for caching.\n- **Vector-stores**: [Qdrant](https://qdrant.tech/) and [Chroma](https://www.trychroma.com/) are currently supported.\n  Vector stores allow for Retrieval-Augmented-Generation (RAG).\n- **Grounding and source-citation:** Access to external documents via vector-stores \n   allows for grounding and source-citation.\n- **Observability, Logging, Lineage:** Langroid generates detailed logs of multi-agent interactions and\n  maintains provenance/lineage of messages, so that you can trace back\n  the origin of a message.\n- **Tools/Plugins/Function-calling**: Langroid supports OpenAI\'s recently\n  released [function calling](https://platform.openai.com/docs/guides/gpt/function-calling)\n  feature. In addition, Langroid has its own native equivalent, which we\n  call **tools** (also known as "plugins" in other contexts). Function\n  calling and tools have the same developer-facing interface, implemented\n  using [Pydantic](https://docs.pydantic.dev/latest/),\n  which makes it very easy to define tools/functions and enable agents\n  to use them. Benefits of using Pydantic are that you never have to write\n  complex JSON specs for function calling, and when the LLM\n  hallucinates malformed JSON, the Pydantic error message is sent back to\n  the LLM so it can fix it!\n\n--- \n\n# :gear: Installation and Setup\n\n## Install `langroid` \nUse `pip` to install `langroid` (from PyPi) to your virtual environment:\n```bash\npip install langroid\n```\nThe core Langroid package lets you use OpenAI Embeddings models via their API. \nIf you instead want to use the `all-MiniLM-L6-v2` embeddings model\nfrom from HuggingFace, install Langroid like this:\n```bash\npip install langroid[hf-embeddings]\n```\nNote that this will install `torch` and `sentence-transfoemers` libraries.\n\n## Set up environment variables (API keys, etc)\n\nCopy the `.env-template` file to a new file `.env` and \ninsert these secrets:\n- **OpenAI API** key (required): If you don\'t have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).\n- **Qdrant** Vector Store API Key (required for apps that need retrieval from\n  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io).\n  Alternatively [Chroma](https://docs.trychroma.com/) is also currently supported. \n  We use the local-storage version of Chroma, so there is no need for an API key.\n- **GitHub** Personal Access Token (required for apps that need to analyze git\n  repos; token-based API calls are less rate-limited). See this\n  [GitHub page](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).\n- **Redis** Password (optional, only needed to cache LLM API responses):\n  Redis [offers](https://redis.com/try-free/) a free 30MB Redis account\n  which is more than sufficient to try out Langroid and even beyond.\n  \n```bash\ncp .env-template .env\n# now edit the .env file, insert your secrets as above\n``` \nYour `.env` file should look like this:\n```bash\nOPENAI_API_KEY=<your key>\nGITHUB_ACCESS_TOKEN=<your token>\nREDIS_PASSWORD=<your password>\nQDRANT_API_KEY=<your key>\n```\n\nCurrently only OpenAI models are supported. Others will be added later\n(Pull Requests welcome!).\n\n---\n\n# :tada: Usage Examples\n\nThese are quick teasers to give a glimpse of what you can do with Langroid\nand how your code would look. \n\n:warning: The code snippets below are intended to give a flavor of the code\nand they are **not** complete runnable examples! For that we encourage you to \nconsult the [`langroid-examples`](https://github.com/langroid/langroid-examples) \nrepository.\n\nAlso see the\n[`Getting Started Guide`](https://langroid.github.io/langroid/quick-start/)\nfor a detailed tutorial. \n\n- [Direct chat with LLM](#direct-llm)\n- [Simple Agent and Task](#agent-task)\n- [Three Communicating Agents](#three-agents)\n- [Agent with Tool/Function-calling](#agent-tool)\n- [Extract Structured Info with Tool/Function-calling](#agent-tool-structured)\n- [Retrieval-Augmented-Generation: Chat with Docs](#agent-rag)\n\n---\n\n## Direct interaction with OpenAI LLM <a name="direct-llm"></a>\n\n```python\nfrom langroid.language_models.openai_gpt import ( \n        OpenAIGPTConfig, OpenAIChatModel, OpenAIGPT,\n)\nfrom langroid.language_models.base import LLMMessage, Role\n\ncfg = OpenAIGPTConfig(chat_model=OpenAIChatModel.GPT4)\n\nmdl = OpenAIGPT(cfg)\n\nmessages = [\n  LLMMessage(content="You are a helpful assistant",  role=Role.SYSTEM), \n  LLMMessage(content="What is the capital of Ontario?",  role=Role.USER),\n]\nresponse = mdl.chat(messages, max_tokens=200)\nprint(response.message)\n```\n\n---\n\n## Define an agent, set up a task, and run it <a name="agent-task"></a>\n\n```python\nfrom langroid.agent.chat_agent import ChatAgent, ChatAgentConfig\nfrom langroid.agent.task import Task\nfrom langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig\n\nconfig = ChatAgentConfig(\n    llm = OpenAIGPTConfig(\n        chat_model=OpenAIChatModel.GPT4,\n    ),\n    vecdb=None, # no vector store\n)\nagent = ChatAgent(config)\n# get response from agent\'s LLM, and put this in an interactive loop...\n# answer = agent.llm_response("What is the capital of Ontario?")\n  # ... OR instead, set up a task (which has a built-in loop) and run it\ntask = Task(agent, name="Bot") \ntask.run() # ... a loop seeking response from LLM or User at each turn\n```\n\n---\n\n## Three communicating agents <a name="three-agents"></a>\n\nA toy numbers game, where when given a number `n`:\n- `repeater_agent`\'s LLM simply returns `n`,\n- `even_agent`\'s LLM returns `n/2` if `n` is even, else says "DO-NOT-KNOW"\n- `odd_agent`\'s LLM returns `3*n+1` if `n` is odd, else says "DO-NOT-KNOW"\n\nFirst define the 3 agents, and set up their tasks with instructions:\n\n```python\nfrom langroid.utils.constants import NO_ANSWER\nfrom langroid.agent.chat_agent import ChatAgent, ChatAgentConfig\nfrom langroid.agent.task import Task\nfrom langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig\nconfig = ChatAgentConfig(\n    llm = OpenAIGPTConfig(\n        chat_model=OpenAIChatModel.GPT4,\n    ),\n    vecdb = None,\n)\nrepeater_agent = ChatAgent(config)\nrepeater_task = Task(\n    repeater_agent,\n    name = "Repeater",\n    system_message="""\n    Your job is to repeat whatever number you receive.\n    """,\n    llm_delegate=True, # LLM takes charge of task\n    single_round=False, \n)\neven_agent = ChatAgent(config)\neven_task = Task(\n    even_agent,\n    name = "EvenHandler",\n    system_message=f"""\n    You will be given a number. \n    If it is even, divide by 2 and say the result, nothing else.\n    If it is odd, say {NO_ANSWER}\n    """,\n    single_round=True,  # task done after 1 step() with valid response\n)\n\nodd_agent = ChatAgent(config)\nodd_task = Task(\n    odd_agent,\n    name = "OddHandler",\n    system_message=f"""\n    You will be given a number n. \n    If it is odd, return (n*3+1), say nothing else. \n    If it is even, say {NO_ANSWER}\n    """,\n    single_round=True,  # task done after 1 step() with valid response\n)\n```\nThen add the `even_task` and `odd_task` as sub-tasks of `repeater_task`, \nand run the `repeater_task`, kicking it off with a number as input:\n```python\nrepeater_task.add_sub_task([even_task, odd_task])\nrepeater_task.run("3")\n```\n---\n\n## Simple Tool/Function-calling example <a name="agent-tool"></a>\n\nLangroid leverages Pydantic to support OpenAI\'s\n[Function-calling API](https://platform.openai.com/docs/guides/gpt/function-calling)\nas well as its own native tools. The benefits are that you don\'t have to write\nany JSON to specify the schema, and also if the LLM hallucinates a malformed\ntool syntax, Langroid sends the Pydantic validation error (suitiably sanitized) \nto the LLM so it can fix it!\n\nSimple example: Say the agent has a secret list of numbers, \nand we want the LLM to find the smallest number in the list. \nWe want to give the LLM a `probe` tool/function which takes a\nsingle number `n` as argument. The tool handler method in the agent\nreturns how many numbers in its list are at most `n`.\n\nFirst define the tool using Langroid\'s `ToolMessage` class:\n\n\n```python\nfrom langroid.agent.tool_message import ToolMessage\nclass ProbeTool(ToolMessage):\n  request: str = "probe" # specifies which agent method handles this tool\n  purpose: str = """\n        To find how many numbers in my list are less than or equal to  \n        the <number> you specify.\n        """ # description used to instruct the LLM on when/how to use the tool\n  number: int  # required argument to the tool\n```\n\nThen define a `SpyGameAgent` as a subclass of `ChatAgent`, \nwith a method `probe` that handles this tool:\n\n```python\nfrom langroid.agent.chat_agent import ChatAgent, ChatAgentConfig\nclass SpyGameAgent(ChatAgent):\n  def __init__(self, config: ChatAgentConfig):\n    super().__init__(config)\n    self.numbers = [3, 4, 8, 11, 15, 25, 40, 80, 90]\n\n  def probe(self, msg: ProbeTool) -> str:\n    # return how many numbers in self.numbers are less or equal to msg.number\n    return str(len([n for n in self.numbers if n <= msg.number]))\n```\n\nWe then instantiate the agent and enable it to use and respond to the tool:\n\n```python\nfrom langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig\nspy_game_agent = SpyGameAgent(\n    ChatAgentConfig(\n        name="Spy",\n        llm = OpenAIGPTConfig(\n            chat_model=OpenAIChatModel.GPT4,\n        ),\n        vecdb=None,\n        use_tools=False, #  don\'t use Langroid native tool\n        use_functions_api=True, # use OpenAI function-call API\n    )\n)\nspy_game_agent.enable_message(ProbeTool)\n```\n\nFor a full working example see the\n[chat-agent-tool.py](https://github.com/langroid/langroid-examples/blob/main/examples/quick-start/chat-agent-tool.py)\nscript in the `langroid-examples` repo.\n\n---\n\n## Tool/Function-calling to extract structured information from text <a name="agent-tool-structured"></a>\n\nSuppose you want an agent to extract \nthe key terms of a lease, from a lease document, as a nested JSON structure.\nFirst define the desired structure via Pydantic models:\n\n```python\nfrom pydantic import BaseModel\nclass LeasePeriod(BaseModel):\n    start_date: str\n    end_date: str\n\n\nclass LeaseFinancials(BaseModel):\n    monthly_rent: str\n    deposit: str\n\nclass Lease(BaseModel):\n    period: LeasePeriod\n    financials: LeaseFinancials\n    address: str\n```\n\nThen define the `LeaseMessage` tool as a subclass of Langroid\'s `ToolMessage`.\nNote the tool has a required argument `terms` of type `Lease`:\n\n```python\nclass LeaseMessage(ToolMessage):\n    request: str = "lease_info"\n    purpose: str = """\n        Collect information about a Commercial Lease.\n        """\n    terms: Lease\n```\n\nThen define a `LeaseExtractorAgent` with a method `lease_info` that handles this tool,\ninstantiate the agent, and enable it to use and respond to this tool:\n\n```python\nclass LeaseExtractorAgent(ChatAgent):\n    def lease_info(self, message: LeaseMessage) -> str:\n        print(\n            f"""\n        DONE! Successfully extracted Lease Info:\n        {message.terms}\n        """\n        )\n        return json.dumps(message.terms.dict())\n    \nlease_extractor_agent = LeaseExtractorAgent(\n  ChatAgentConfig(\n    llm=OpenAIGPTConfig(),\n    use_functions_api=False,\n    use_tools=True,\n  )\n)\nlease_extractor_agent.enable_message(LeaseMessage)\n```\n\nSee the [`chat_multi_extract.py`](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py)\nscript in the `langroid-examples` repo for a full working example.\n\n---\n\n## Chat with documents (file paths, URLs, etc) <a name="agent-docs"></a>\n\nLangroid provides a specialized agent class `DocChatAgent` for this purpose.\nIt incorporates document sharding, embedding, storage in a vector-DB, \nand retrieval-augmented query-answer generation.\nUsing this class to chat with a collection of documents is easy.\nFirst create a `DocChatAgentConfig` instance, with a \n`doc_paths` field that specifies the documents to chat with.\n\n```python\nfrom langroid.agent.doc_chat_agent import DocChatAgentConfig\nconfig = DocChatAgentConfig(\n  doc_paths = [\n    "https://en.wikipedia.org/wiki/Language_model",\n    "https://en.wikipedia.org/wiki/N-gram_language_model",\n    "/path/to/my/notes-on-language-models.txt",\n  ]\n  llm = OpenAIGPTConfig(\n    chat_model=OpenAIChatModel.GPT4,\n  ),\n  vecdb=VectorStoreConfig(\n    type="qdrant",\n  ),\n)\n```\n\nThen instantiate the `DocChatAgent`, ingest the docs into the vector-store:\n\n```python\nagent = DocChatAgent(config)\nagent.ingest()\n```\nThen we can either ask the agent one-off questions,\n```python\nagent.chat("What is a language model?")\n```\nor wrap it in a `Task` and run an interactive loop with the user:\n```python\nfrom langroid.task import Task\ntask = Task(agent)\ntask.run()\n```\n\nSee full working scripts in the \n[`docqa`](https://github.com/langroid/langroid-examples/tree/main/examples/docqa)\nfolder of the `langroid-examples` repo.\n\n---\n\n# Contributors\n\n- Prasad Chalasani (IIT BTech/CS, CMU PhD/ML; Independent ML Consultant)\n- Somesh Jha (IIT BTech/CS, CMU PhD/CS; Professor of CS, U Wisc at Madison)\n- Mohannad Alhanahnah (Research Associate, U Wisc at Madison)\n- Ashish Hooda (IIT BTech/CS; PhD Candidate, U Wisc at Madison)\n\n',
+    'author': 'Prasad Chalasani',
+    'author_email': 'pchalasani@gmail.com',
+    'maintainer': 'None',
+    'maintainer_email': 'None',
+    'url': 'None',
+    'packages': packages,
+    'package_data': package_data,
+    'install_requires': install_requires,
+    'extras_require': extras_require,
+    'python_requires': '>=3.8.1,<3.12',
+}
+
+
+setup(**setup_kwargs)

langroid-0.1.22/setup.py

@@ -1,85 +0,0 @@
-# -*- coding: utf-8 -*-
-from setuptools import setup
-
-packages = \
-['langroid',
- 'langroid.agent',
- 'langroid.agent.special',
- 'langroid.cachedb',
- 'langroid.embedding_models',
- 'langroid.language_models',
- 'langroid.parsing',
- 'langroid.prompts',
- 'langroid.scripts',
- 'langroid.utils',
- 'langroid.utils.llms',
- 'langroid.utils.output',
- 'langroid.utils.web',
- 'langroid.vector_store']
-
-package_data = \
-{'': ['*']}
-
-install_requires = \
-['autopep8>=2.0.2,<3.0.0',
- 'black[jupyter]>=23.3.0,<24.0.0',
- 'bs4>=0.0.1,<0.0.2',
- 'chromadb>=0.3.21,<0.4.0',
- 'colorlog>=6.7.0,<7.0.0',
- 'faker>=18.9.0,<19.0.0',
- 'fakeredis>=2.12.1,<3.0.0',
- 'fire>=0.5.0,<0.6.0',
- 'flake8>=6.0.0,<7.0.0',
- 'halo>=0.0.31,<0.0.32',
- 'mkdocs-awesome-pages-plugin>=2.8.0,<3.0.0',
- 'mkdocs-gen-files>=0.4.0,<0.5.0',
- 'mkdocs-jupyter>=0.24.1,<0.25.0',
- 'mkdocs-literate-nav>=0.6.0,<0.7.0',
- 'mkdocs-material>=9.1.5,<10.0.0',
- 'mkdocs-section-index>=0.3.5,<0.4.0',
- 'mkdocs>=1.4.2,<2.0.0',
- 'mkdocstrings[python]>=0.21.2,<0.22.0',
- 'mypy>=1.2.0,<2.0.0',
- 'nltk>=3.8.1,<4.0.0',
- 'openai>=0.27.5,<0.28.0',
- 'pre-commit>=3.3.2,<4.0.0',
- 'pydantic==1.10.11',
- 'pygithub>=1.58.1,<2.0.0',
- 'pygments>=2.15.1,<3.0.0',
- 'pyparsing>=3.0.9,<4.0.0',
- 'python-dotenv>=1.0.0,<2.0.0',
- 'qdrant-client>=1.3.1,<2.0.0',
- 'redis>=4.5.5,<5.0.0',
- 'requests-oauthlib>=1.3.1,<2.0.0',
- 'requests>=2.31.0,<3.0.0',
- 'rich>=13.3.4,<14.0.0',
- 'ruff>=0.0.270,<0.0.271',
- 'tiktoken>=0.3.3,<0.4.0',
- 'trafilatura>=1.5.0,<2.0.0',
- 'typer>=0.7.0,<0.8.0',
- 'types-redis>=4.5.5.2,<5.0.0.0',
- 'types-requests>=2.31.0.1,<3.0.0.0',
- 'wget>=3.2,<4.0']
-
-extras_require = \
-{'hf-embeddings': ['sentence-transformers==2.2.2', 'torch==2.0.0']}
-
-setup_kwargs = {
-    'name': 'langroid',
-    'version': '0.1.22',
-    'description': 'Harness LLMs with Multi-Agent Programming',
-    'long_description': '<div style="display: flex; align-items: center;">\n  <img src="docs/assets/orange-logo.png" alt="Logo" \n        width="80" height="80"align="left">\n  <h1>Langroid: Harness LLMs with Multi-Agent Programming</h1>\n</div>\n\n[![Pytest](https://github.com/langroid/langroid/actions/workflows/pytest.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/pytest.yml)\n[![Lint](https://github.com/langroid/langroid/actions/workflows/validate.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/validate.yml)\n[![Docs](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/mkdocs-deploy.yml)\n\nLangroid is an intuitive, lightweight, transparent, flexible, extensible and principled\nPython framework to harness LLMs using Multi-Agent Programming (MAP).\nWe welcome [contributions](CONTRIBUTING.md)!\n\nDocumentation: https://langroid.github.io/langroid/\n\nUsage examples: https://github.com/langroid/langroid-examples\n\n## Overview\n\n### The LLM Opportunity\n\nGiven the remarkable abilities of recent Large Language Models (LLMs), there\nis an unprecedented opportunity to build intelligent applications powered by\nthis transformative technology. The top question for any enterprise is: how\nbest to harness the power of LLMs for complex applications? For technical and\npractical reasons, building LLM-powered applications is not as simple as\nthrowing a task at an LLM-system and expecting it to do it.\n\n### Langroid\'s Multi-Agent Programming Framework\n\nEffectively leveraging LLMs at scale requires a *principled programming\nframework*. In particular, there is often a need to maintain multiple LLM\nconversations, each instructed in different ways, and "responsible" for\ndifferent aspects of a task.\n\nAn *agent* is a convenient abstraction that encapsulates LLM conversation\nstate, along with access to long-term memory (vector-stores) and tools (a.k.a functions\nor plugins). Thus a **Multi-Agent Programming** framework is a natural fit\nfor complex LLM-based applications.\n\n> Langroid is the first Python LLM-application framework that was explicitly\ndesigned  with Agents as first-class citizens, and Multi-Agent Programming\nas the core  design principle. The framework is inspired by ideas from the\n[Actor Framework](https://en.wikipedia.org/wiki/Actor_model).\n\nLangroid allows an intuitive definition of agents, tasks and task-delegation\namong agents. There is a principled mechanism to orchestrate multi-agent\ncollaboration. Agents act as message-transformers, and take turns responding to (and\ntransforming) the current message. The architecture is lightweight, transparent,\nflexible, and allows other types of orchestration to be implemented.\nBesides Agents, Langroid also provides simple ways to directly interact with  \nLLMs and vector-stores.\n\n### Highlights\nHighlights of Langroid\'s features as of July 2023:\n\n- **Agents as first-class citizens:** The `Agent` class encapsulates LLM conversation state,\n  and optionally a vector-store and tools. Agents are a core abstraction in Langroid;\n  Agents act as _message transformers_, and by default provide 3 _responder_ methods,  \n  one corresponding to each entity: LLM, Agent, User.\n- **Tasks:** A Task class wraps an Agent, and gives the agent instructions (or roles, or goals), \n  manages iteration over an Agent\'s responder methods, \n  and orchestrates multi-agent interactions via hierarchical, recursive\n  task-delegation. The `Task.run()` method has the same \n  type-signature as an Agent\'s responder\'s methods, and this is key to how \n  a task of an agent can delegate to other sub-tasks: from the point of view of a Task,\n  sub-tasks are simply additional responders, to be used in a round-robin fashion \n  after the agent\'s own responders.\n- **Modularity, Reusabilily, Loose coupling:** The `Agent` and `Task` abstractions allow users to design\n  Agents with specific skills, wrap them in Tasks, and combine tasks in a flexible way.\n- **LLM Support**: Langroid supports OpenAI LLMs including GPT-3.5-Turbo,\n  GPT-4-0613\n- **Caching of LLM prompts, responses:** Langroid uses [Redis](https://redis.com/try-free/) for caching.\n- **Vector-stores**: [Qdrant](https://qdrant.tech/) and [Chroma](https://www.trychroma.com/) are currently supported.\n  Vector stores allow for Retrieval-Augmented-Generaation (RAG).\n- **Grounding and source-citation:** Access to external documents via vector-stores \n   allows for grounding and source-citation.\n- **Observability, Logging, Lineage:** Langroid generates detailed logs of multi-agent interactions and\n  maintains provenance/lineage of messages, so that you can trace back\n  the origin of a message.\n- **Tools/Plugins/Function-calling**: Langroid supports OpenAI\'s recently\n  released [function calling](https://platform.openai.com/docs/guides/gpt/function-calling)\n  feature. In addition, Langroid has its own native equivalent, which we\n  call **tools** (also known as "plugins" in other contexts). Function\n  calling and tools have the same developer-facing interface, implemented\n  using [Pydantic](https://docs.pydantic.dev/latest/),\n  which makes it very easy to define tools/functions and enable agents\n  to use them. Benefits of using Pydantic are that you never have to write\n  complex JSON specs for function calling, and when the LLM\n  hallucinates malformed JSON, the Pydantic error message is sent back to\n  the LLM so it can fix it!\n\n# Usage/quick-start\nThese are quick teasers to give a glimpse of what you can do with Langroid\nand how your code would look. See the \n[`Getting Started Guide`](https://langroid.github.io/langroid/getting_started/)\nfor a detailed tutorial.\n\n## Install `langroid` \nUse `pip` to install `langroid` (from PyPi) to your virtual environment:\n```bash\npip install langroid\n```\nThe core Langroid package lets you use OpenAI Embeddings models via their API. \nIf you instead want to use the `all-MiniLM-L6-v2` embeddings model\nfrom from HuggingFace, install Langroid like this:\n```bash\npip install langroid[hf-embeddings]\n```\nNote that this will install `torch` and `sentence-transfoemers` libraries.\n\n## Set up environment variables (API keys, etc)\n\nCopy the `.env-template` file to a new file `.env` and \ninsert these secrets:\n- **OpenAI API** key (required): If you don\'t have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).\n- **Qdrant** Vector Store API Key (required for apps that need retrieval from\n  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io)\n  Alternatively [Chroma](https://docs.trychroma.com/) is also currently supported. \n  We use the local-storage version of Chroma, so there is no need for an API key.\n- **GitHub** Personal Access Token (required for apps that need to analyze git\n  repos; token-based API calls are less rate-limited). See this\n  [GitHub page](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).\n- **Redis** Password (optional, only needed to cache LLM API responses):\n  Redis [offers](https://redis.com/try-free/) a free 30MB Redis account\n  which is more than sufficient to try out Langroid and even beyond.\n  \n```bash\ncp .env-template .env\n# now edit the .env file, insert your secrets as above\n``` \nYour `.env` file should look like this:\n```bash\nOPENAI_API_KEY=<your key>\nGITHUB_ACCESS_TOKEN=<your token>\nREDIS_PASSWORD=<your password>\nQDRANT_API_KEY=<your key>\n```\n\nCurrently only OpenAI models are supported. Others will be added later\n(Pull Requests welcome!).\n\n## Direct interaction with OpenAI LLM\n\n```python\nfrom langroid.language_models.openai_gpt import ( \n        OpenAIGPTConfig, OpenAIChatModel, OpenAIGPT,\n)\nfrom langroid.language_models.base import LLMMessage, Role\n\ncfg = OpenAIGPTConfig(chat_model=OpenAIChatModel.GPT4)\n\nmdl = OpenAIGPT(cfg)\n\nmessages = [\n  LLMMessage(content="You are a helpful assistant",  role=Role.SYSTEM), \n  LLMMessage(content="What is the capital of Ontario?",  role=Role.USER),\n],\nresponse = mdl.chat(messages, max_tokens=200)\n```\n\n## Define an agent, set up a task, and run it\n\n```python\nfrom langroid.agent.chat_agent import ChatAgent, ChatAgentConfig\nfrom langroid.agent.task import Task\nfrom langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig\n\nconfig = ChatAgentConfig(\n    llm = OpenAIGPTConfig(\n        chat_model=OpenAIChatModel.GPT4,\n    ),\n    vecdb=None, # no vector store\n)\nagent = ChatAgent(config)\n# get response from agent\'s LLM, and put this in an interactive loop...\nanswer = agent.llm_response("What is the capital of Ontario?")\n# ... or set up a task (which has a built-in loop) and run it\ntask = Task(agent, name="Bot") \ntask.run() # ... a loop seeking response from Agent, LLM or User at each turn\n```\n\n## Three communicating agents\n\nA toy numbers game, where when given a number `n`:\n- `repeater_agent`\'s LLM simply returns `n`,\n- `even_agent`\'s LLM returns `n/2` if `n` is even, else says "DO-NOT-KNOW"\n- `odd_agent`\'s LLM returns `3*n+1` if `n` is odd, else says "DO-NOT-KNOW"\n\nFirst define the 3 agents, and set up their tasks with instructions:\n\n```python\n    config = ChatAgentConfig(\n        llm = OpenAIGPTConfig(\n            chat_model=OpenAIChatModel.GPT4,\n        ),\n        vecdb = None,\n    )\n    repeater_agent = ChatAgent(config)\n    repeater_task = Task(\n        repeater_agent,\n        name = "Repeater",\n        system_message="""\n        Your job is to repeat whatever number you receive.\n        """,\n        llm_delegate=True, # LLM takes charge of task\n        single_round=False, \n    )\n    even_agent = ChatAgent(config)\n    even_task = Task(\n        even_agent,\n        name = "EvenHandler",\n        system_message=f"""\n        You will be given a number. \n        If it is even, divide by 2 and say the result, nothing else.\n        If it is odd, say {NO_ANSWER}\n        """,\n        single_round=True,  # task done after 1 step() with valid response\n    )\n\n    odd_agent = ChatAgent(config)\n    odd_task = Task(\n        odd_agent,\n        name = "OddHandler",\n        system_message=f"""\n        You will be given a number n. \n        If it is odd, return (n*3+1), say nothing else. \n        If it is even, say {NO_ANSWER}\n        """,\n        single_round=True,  # task done after 1 step() with valid response\n    )\n```\nThen add the `even_task` and `odd_task` as sub-tasks of `repeater_task`, \nand run the `repeater_task`, kicking it off with a number as input:\n```python\n    repeater_task.add_sub_task([even_task, odd_task])\n    repeater_task.run("3")\n```\n\n### Simple Tool/Function-calling example\nLangroid leverages Pydantic to support OpenAI\'s\n[Function-calling API](https://platform.openai.com/docs/guides/gpt/function-calling)\nas well as its own native tools.\n\nSimple example: Say the agent has a secret list of numbers, \nand we want the LLM to find the smallest number in the list. \nWe want to give the LLM a `probe` tool/function which takes a\nsingle number `n` as argument. The tool handler method in the agent\nreturns how many numbers in its list are at most `n`.\n\nFirst define the tool using Langroid\'s `ToolMessage` class:\n\n\n```python\nfrom langroid.agent.tool_message import ToolMessage\nclass ProbeTool(ToolMessage):\n  request: str = "probe" # specifies which agent method handles this tool\n  purpose: str = """\n        To find how many numbers in my list are less than or equal to  \n        the <number> you specify.\n        """ # description used to instruct the LLM on when/how to use the tool\n  number: int  # required argument to the tool\n```\n\nThen define a `SpyGameAgent` as a subclass of `ChatAgent`, \nwith a method `probe` that handles this tool:\n\n```python\nfrom langroid.agent.chat_agent import ChatAgent, ChatAgentConfig\nclass SpyGameAgent(ChatAgent):\n  def __init__(self, config: ChatAgentConfig):\n    super().__init__(config)\n    self.numbers = [3, 4, 8, 11, 15, 25, 40, 80, 90]\n\n  def probe(self, msg: ProbeTool) -> str:\n    # return how many numbers in self.numbers are less or equal to msg.number\n    return str(len([n for n in self.numbers if n <= msg.number]))\n```\n\nWe then instantiate the agent and enable it to use and respond to the tool:\n\n```python\nfrom langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig\nspy_game_agent = SpyGameAgent(\n    ChatAgentConfig(\n        name="Spy",\n        llm = OpenAIGPTConfig(\n            chat_model=OpenAIChatModel.GPT4,\n        ),\n        vecdb=None,\n        use_tools=False, #  don\'t use Langroid native tool\n        use_functions_api=True, # use OpenAI function-call API\n    )\n)\nspy_game_agent.enable_message(ProbeTool)\n```\n\nFor a full working example see the\n[chat-agent-tool.py](https://github.com/langroid/langroid-examples/blob/main/examples/quick-start/chat-agent-tool.py)\nscript in the `langroid-examples` repo.\n\n### Tool/Function-calling to extract structured information from text\n\nSuppose you want an agent to extract \nthe key terms of a lease, from a lease document, as a nested JSON structure.\nFirst define the desired structure via Pydantic models:\n\n```python\nfrom pydantic import BaseModel\nclass LeasePeriod(BaseModel):\n    start_date: str\n    end_date: str\n\n\nclass LeaseFinancials(BaseModel):\n    monthly_rent: str\n    deposit: str\n\nclass Lease(BaseModel):\n    period: LeasePeriod\n    financials: LeaseFinancials\n    address: str\n```\n\nThen define the `LeaseMessage` tool as a subclass of Langroid\'s `ToolMessage`.\nNote the tool as a required argument `terms` of type `Lease`:\n\n```python\nclass LeaseMessage(ToolMessage):\n    request: str = "lease_info"\n    purpose: str = """\n        Collect information about a Commercial Lease.\n        """\n    terms: Lease\n```\n\nThen define a `LeaseExtractorAgent` with a method `lease_info` that handles this tool,\ninstantiate the agent, and enable it to use and respond to this tool:\n\n```python\nclass LeaseExtractorAgent(ChatAgent):\n    def lease_info(self, message: LeaseMessage) -> str:\n        print(\n            f"""\n        DONE! Successfully extracted Lease Info:\n        {message.terms}\n        """\n        )\n        return json.dumps(message.terms.dict())\n    \nlease_extractor_agent = LeaseExtractorAgent(\n  ChatAgentConfig(\n    llm=OpenAIGPTConfig(),\n    use_functions_api=False,\n    use_tools=True,\n  )\n)\nlease_extractor_agent.enable_message(LeaseMessage)\n```\n\nSee the [`chat_multi_extract.py`](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py)\nscript in the `langroid-examples` repo for a full working example.\n\n\n### Chat with documents (file paths, URLs, etc)\n\nLangroid provides a specialized agent class `DocChatAgent` for this purpose.\nIt incorporates document sharding, embedding, storage in a vector-DB, \nand retrieval-augmented query-answer generation.\nUsing this class to chat with a collection of documents is easy.\nFirst create a `DocChatAgentConfig` instance, with a \n`doc_paths` field that specifies the documents to chat with.\n\n```python\nfrom langroid.agent.doc_chat_agent import DocChatAgentConfig\nconfig = DocChatAgentConfig(\n  doc_paths = [\n    "https://en.wikipedia.org/wiki/Language_model",\n    "https://en.wikipedia.org/wiki/N-gram_language_model",\n    "/path/to/my/notes-on-language-models.txt",\n  ]\n  llm = OpenAIGPTConfig(\n    chat_model=OpenAIChatModel.GPT4,\n  ),\n  vecdb=VectorStoreConfig(\n    type="qdrant",\n  ),\n)\n```\n\nThen instantiate the `DocChatAgent`, ingest the docs into the vector-store:\n\n```python\nagent = DocChatAgent(config)\nagent.ingest()\n```\nThen we can either ask the agent one-off questions,\n```python\nagent.chat("What is a language model?")\n```\nor wrap it in a `Task` and run an interactive loop with the user:\n```python\nfrom langroid.task import Task\ntask = Task(agent)\ntask.run()\n```\n\nSee full working scripts in the \n[`docqa`](https://github.com/langroid/langroid-examples/tree/main/examples/docqa)\nfolder of the `langroid-examples` repo.\n\n\n## Contributors\n\n- Prasad Chalasani (IIT BTech/CS, CMU PhD/ML; Independent ML Consultant)\n- Somesh Jha (IIT BTech/CS, CMU PhD/CS; Professor of CS, U Wisc at Madison)\n- Mohannad Alhanahnah (Research Associate, U Wisc at Madison)\n- Ashish Hooda (IIT BTech/CS; PhD Candidate, U Wisc at Madison)\n\n',
-    'author': 'Prasad Chalasani',
-    'author_email': 'pchalasani@gmail.com',
-    'maintainer': 'None',
-    'maintainer_email': 'None',
-    'url': 'None',
-    'packages': packages,
-    'package_data': package_data,
-    'install_requires': install_requires,
-    'extras_require': extras_require,
-    'python_requires': '>=3.8.1,<3.12',
-}
-
-
-setup(**setup_kwargs)