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

{langroid-0.1.139.dist-info → langroid-0.1.219.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.139
+Version: 0.1.219
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -10,80 +10,101 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Provides-Extra: chainlit
+Provides-Extra: chromadb
 Provides-Extra: hf-embeddings
 Provides-Extra: litellm
+Provides-Extra: metaphor
+Provides-Extra: mkdocs
 Provides-Extra: mysql
+Provides-Extra: neo4j
 Provides-Extra: postgres
+Provides-Extra: sciphi
+Provides-Extra: transformers
+Provides-Extra: unstructured
+Requires-Dist: agent-search (>=0.0.7,<0.0.8) ; extra == "sciphi"
+Requires-Dist: aiohttp (>=3.9.1,<4.0.0)
 Requires-Dist: async-generator (>=1.10,<2.0)
 Requires-Dist: autopep8 (>=2.0.2,<3.0.0)
-Requires-Dist: black[jupyter] (>=23.3.0,<24.0.0)
+Requires-Dist: black[jupyter] (>=24.3.0,<25.0.0)
 Requires-Dist: bs4 (>=0.0.1,<0.0.2)
-Requires-Dist: chromadb (==0.3.21)
+Requires-Dist: chainlit (>=1.0.400,<2.0.0) ; extra == "chainlit"
+Requires-Dist: chromadb (>=0.4.21,<=0.4.23) ; extra == "chromadb"
 Requires-Dist: colorlog (>=6.7.0,<7.0.0)
 Requires-Dist: docstring-parser (>=0.15,<0.16)
+Requires-Dist: duckduckgo-search (>=4.4,<5.0)
 Requires-Dist: faker (>=18.9.0,<19.0.0)
 Requires-Dist: fakeredis (>=2.12.1,<3.0.0)
-Requires-Dist: farm-haystack[file-conversion,ocr,pdf,preprocessing] (>=1.21.1,<2.0.0)
 Requires-Dist: fire (>=0.5.0,<0.6.0)
 Requires-Dist: flake8 (>=6.0.0,<7.0.0)
 Requires-Dist: google-api-python-client (>=2.95.0,<3.0.0)
+Requires-Dist: grpcio (>=1.62.1,<2.0.0)
 Requires-Dist: halo (>=0.0.31,<0.0.32)
+Requires-Dist: huggingface-hub (>=0.21.2,<0.22.0) ; extra == "transformers"
 Requires-Dist: jinja2 (>=3.1.2,<4.0.0)
-Requires-Dist: lancedb (>=0.3.0,<0.4.0)
-Requires-Dist: litellm (>=1.0.0,<2.0.0) ; extra == "litellm"
+Requires-Dist: lancedb (>=0.6.2,<0.7.0)
+Requires-Dist: litellm (>=1.30.1,<2.0.0) ; extra == "litellm"
 Requires-Dist: lxml (>=4.9.3,<5.0.0)
 Requires-Dist: meilisearch (>=0.28.3,<0.29.0)
-Requires-Dist: meilisearch-python-sdk (>=2.0.1,<3.0.0)
-Requires-Dist: mkdocs (>=1.4.2,<2.0.0)
-Requires-Dist: mkdocs-awesome-pages-plugin (>=2.8.0,<3.0.0)
-Requires-Dist: mkdocs-gen-files (>=0.4.0,<0.5.0)
-Requires-Dist: mkdocs-jupyter (>=0.24.1,<0.25.0)
-Requires-Dist: mkdocs-literate-nav (>=0.6.0,<0.7.0)
-Requires-Dist: mkdocs-material (>=9.1.5,<10.0.0)
-Requires-Dist: mkdocs-rss-plugin (>=1.8.0,<2.0.0)
-Requires-Dist: mkdocs-section-index (>=0.3.5,<0.4.0)
-Requires-Dist: mkdocstrings[python] (>=0.21.2,<0.22.0)
+Requires-Dist: meilisearch-python-sdk (>=2.2.3,<3.0.0)
+Requires-Dist: metaphor-python (>=0.1.23,<0.2.0) ; extra == "metaphor"
+Requires-Dist: mkdocs (>=1.4.2,<2.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-awesome-pages-plugin (>=2.8.0,<3.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-gen-files (>=0.4.0,<0.5.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-jupyter (>=0.24.1,<0.25.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-literate-nav (>=0.6.0,<0.7.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-material (>=9.1.5,<10.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-rss-plugin (>=1.8.0,<2.0.0) ; extra == "mkdocs"
+Requires-Dist: mkdocs-section-index (>=0.3.5,<0.4.0) ; extra == "mkdocs"
+Requires-Dist: mkdocstrings[python] (>=0.21.2,<0.22.0) ; extra == "mkdocs"
 Requires-Dist: momento (>=1.10.2,<2.0.0)
 Requires-Dist: mypy (>=1.7.0,<2.0.0)
+Requires-Dist: neo4j (>=5.14.1,<6.0.0) ; extra == "neo4j"
 Requires-Dist: nltk (>=3.8.1,<4.0.0)
 Requires-Dist: onnxruntime (==1.16.1)
-Requires-Dist: openai (>=1.2.3,<2.0.0)
+Requires-Dist: openai (>=1.14.0,<2.0.0)
 Requires-Dist: pandas (>=2.0.3,<3.0.0)
+Requires-Dist: pdf2image (>=1.17.0,<2.0.0)
 Requires-Dist: pdfplumber (>=0.10.2,<0.11.0)
 Requires-Dist: pre-commit (>=3.3.2,<4.0.0)
 Requires-Dist: prettytable (>=3.8.0,<4.0.0)
 Requires-Dist: psycopg2 (>=2.9.7,<3.0.0) ; extra == "postgres"
-Requires-Dist: pydantic (==1.10.11)
+Requires-Dist: pyarrow (==15.0.0)
+Requires-Dist: pydantic (==1.10.13)
 Requires-Dist: pygithub (>=1.58.1,<2.0.0)
 Requires-Dist: pygments (>=2.15.1,<3.0.0)
 Requires-Dist: pymupdf (>=1.23.3,<2.0.0)
 Requires-Dist: pymysql (>=1.1.0,<2.0.0) ; extra == "mysql"
 Requires-Dist: pyparsing (>=3.0.9,<4.0.0)
 Requires-Dist: pypdf (>=3.12.2,<4.0.0)
+Requires-Dist: pytesseract (>=0.3.10,<0.4.0)
 Requires-Dist: pytest-asyncio (>=0.21.1,<0.22.0)
 Requires-Dist: pytest-mysql (>=2.4.2,<3.0.0) ; extra == "mysql"
 Requires-Dist: pytest-postgresql (>=5.0.0,<6.0.0) ; extra == "postgres"
 Requires-Dist: pytest-redis (>=3.0.2,<4.0.0)
+Requires-Dist: python-docx (>=1.1.0,<2.0.0)
 Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
-Requires-Dist: qdrant-client (>=1.7.0,<2.0.0)
+Requires-Dist: python-socketio (>=5.11.0,<6.0.0) ; extra == "chainlit"
+Requires-Dist: qdrant-client (>=1.8.0,<2.0.0)
 Requires-Dist: rank-bm25 (>=0.2.2,<0.3.0)
 Requires-Dist: redis (>=5.0.1,<6.0.0)
 Requires-Dist: requests (>=2.31.0,<3.0.0)
 Requires-Dist: requests-oauthlib (>=1.3.1,<2.0.0)
 Requires-Dist: rich (>=13.3.4,<14.0.0)
-Requires-Dist: ruff (>=0.0.270,<0.0.271)
+Requires-Dist: ruff (>=0.2.2,<0.3.0)
 Requires-Dist: scrapy (>=2.11.0,<3.0.0)
 Requires-Dist: sentence-transformers (==2.2.2) ; extra == "hf-embeddings"
 Requires-Dist: sqlalchemy (>=2.0.19,<3.0.0)
-Requires-Dist: tantivy (==0.20.1)
+Requires-Dist: tantivy (>=0.21.0,<0.22.0)
 Requires-Dist: thefuzz (>=0.20.0,<0.21.0)
 Requires-Dist: tiktoken (>=0.5.1,<0.6.0)
 Requires-Dist: torch (==2.0.0) ; extra == "hf-embeddings"
 Requires-Dist: trafilatura (>=1.5.0,<2.0.0)
 Requires-Dist: typer (>=0.9.0,<0.10.0)
+Requires-Dist: types-pyyaml (>=6.0.12.20240311,<7.0.0.0)
 Requires-Dist: types-redis (>=4.5.5.2,<5.0.0.0)
 Requires-Dist: types-requests (>=2.31.0.1,<3.0.0.0)
-Requires-Dist: unstructured[docx,pdf,pptx] (>=0.10.16,<0.10.18)
+Requires-Dist: unstructured[docx,pdf,pptx] (>=0.10.16,<0.10.18) ; extra == "unstructured"
 Requires-Dist: wget (>=3.2,<4.0)
 Description-Content-Type: text/markdown
 
@@ -134,11 +155,16 @@ This Multi-Agent paradigm is inspired by the
 `Langroid` is a fresh take on LLM app-development, where considerable thought has gone 
 into simplifying the developer experience; it does not use `Langchain`.
 
+:fire: See this [Intro to Langroid](https://lancedb.substack.com/p/langoid-multi-agent-programming-framework)
+blog post from the LanceDB team
+
+
 We welcome contributions -- See the [contributions](./CONTRIBUTING.md) document
 for ideas on what to contribute.
 
-
-Building LLM Applications? [Prasad Chalasani](https://www.linkedin.com/in/pchalasani/) is available for consulting
+Are you building LLM Applications, or want help with Langroid for your company, 
+or want to prioritize Langroid features for your company use-cases? 
+[Prasad Chalasani](https://www.linkedin.com/in/pchalasani/) is available for consulting
 (advisory/development): pchalasani at gmail dot com.
 
 Sponsorship is also accepted via [GitHub Sponsors](https://github.com/sponsors/langroid)
@@ -149,46 +175,49 @@ Sponsorship is also accepted via [GitHub Sponsors](https://github.com/sponsors/l
 This is just a teaser; there's much more, like function-calling/tools, 
 Multi-Agent Collaboration, Structured Information Extraction, DocChatAgent 
 (RAG), SQLChatAgent, non-OpenAI local/remote LLMs, etc. Scroll down or see docs for more.
+See the Langroid Quick-Start [Colab](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb)
+that builds up to a 2-agent information-extraction example using the OpenAI ChatCompletion API. 
+See also this [version](https://colab.research.google.com/drive/190Tk7t4AdY1P9F_NlZ33-YEoGnHweQQ0) that uses the OpenAI Assistants API instead.
 
-:fire: Just released! Updated Langroid Quick-Start [Colab](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb)
-that builds up to a 2-agent chat example using the OpenAI ChatCompletion API. 
-See also this [version](https://colab.research.google.com/drive/190Tk7t4AdY1P9F_NlZ33-YEoGnHweQQ0) 
-that uses the OpenAI Assistants API instead.
+:fire: just released! [Example](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat-multi-extract-local.py) 
+script showing how you can use Langroid multi-agents and tools
+to extract structured information from a document using **only a local LLM**
+(Mistral-7b-instruct-v0.2).
 
 ```python
-from langroid.language_models import  OpenAIGPTConfig, OpenAIChatModel, OpenAIGPT
-from langroid import ChatAgent, ChatAgentConfig, Task
+import langroid as lr
+import langroid.language_models as lm
 
 # set up LLM
-llm_cfg = OpenAIGPTConfig( # or OpenAIAssistant to use Assistant API 
+llm_cfg = lm.OpenAIGPTConfig( # or OpenAIAssistant to use Assistant API 
   # any model served via an OpenAI-compatible API
-  chat_model=OpenAIChatModel.GPT4_TURBO, # or, e.g., "local/ollama/mistral"
+  chat_model=lm.OpenAIChatModel.GPT4_TURBO, # or, e.g., "ollama/mistral"
 )
 # use LLM directly
-mdl = OpenAIGPT(llm_cfg)
+mdl = lm.OpenAIGPT(llm_cfg)
 response = mdl.chat("What is the capital of Ontario?", max_tokens=10)
 
 # use LLM in an Agent
-agent_cfg = ChatAgentConfig(llm=llm_cfg)
-agent = ChatAgent(agent_cfg)
+agent_cfg = lr.ChatAgentConfig(llm=llm_cfg)
+agent = lr.ChatAgent(agent_cfg)
 agent.llm_response("What is the capital of China?") 
 response = agent.llm_response("And India?") # maintains conversation state 
 
 # wrap Agent in a Task to run interactive loop with user (or other agents)
-task = Task(agent, name="Bot", system_message="You are a helpful assistant")
+task = lr.Task(agent, name="Bot", system_message="You are a helpful assistant")
 task.run("Hello") # kick off with user saying "Hello"
 
 # 2-Agent chat loop: Teacher Agent asks questions to Student Agent
-teacher_agent = ChatAgent(agent_cfg)
-teacher_task = Task(
+teacher_agent = lr.ChatAgent(agent_cfg)
+teacher_task = lr.Task(
   teacher_agent, name="Teacher",
   system_message="""
     Ask your student concise numbers questions, and give feedback. 
     Start with a question.
     """
 )
-student_agent = ChatAgent(agent_cfg)
-student_task = Task(
+student_agent = lr.ChatAgent(agent_cfg)
+student_task = lr.Task(
   student_agent, name="Student",
   system_message="Concisely answer the teacher's questions.",
   single_round=True,
@@ -198,11 +227,68 @@ teacher_task.add_sub_task(student_task)
 teacher_task.run()
 ```
 
-<details>
-<summary> <b>:fire: Updates/Releases</b></summary>
+# :fire: Updates/Releases
 
+<details>
+<summary> <b>Click to expand</b></summary>
+
+- **Mar 2024:**
+  - **0.1.216:** Improvements to allow concurrent runs of `DocChatAgent`, see the
+    [`test_doc_chat_agent.py`](https://github.com/langroid/langroid/blob/main/tests/main/test_doc_chat_agent.py)
+    in particular the `test_doc_chat_batch()`;
+    New task run utility: [`run_batch_task_gen`](https://github.com/langroid/langroid/blob/main/langroid/agent/batch.py) 
+    where a task generator can be specified, to generate one task per input. 
+  - **0.1.212:** ImagePdfParser: support for extracting text from image-based PDFs.
+    (this means `DocChatAgent` will now work with image-pdfs).
+  - **0.1.194 - 0.1.211:** Misc fixes, improvements, and features:
+    - Big enhancement in RAG performance (mainly, recall) due to a [fix in Relevance 
+      Extractor](https://github.com/langroid/langroid/releases/tag/0.1.209)
+    - `DocChatAgent` [context-window fixes](https://github.com/langroid/langroid/releases/tag/0.1.208)
+    - Anthropic/Claude3 support via Litellm
+    - `URLLoader`: detect file time from header when URL doesn't end with a 
+      recognizable suffix like `.pdf`, `.docx`, etc.
+    - Misc lancedb integration fixes
+    - Auto-select embedding config based on whether `sentence_transformer` module is available.
+    - Slim down dependencies, make some heavy ones optional, e.g. `unstructured`, 
+      `haystack`, `chromadb`, `mkdocs`, `huggingface-hub`, `sentence-transformers`.
+    - Easier top-level imports from `import langroid as lr`
+    - Improve JSON detection, esp from weak LLMs
+- **Feb 2024:** 
+  - **0.1.193:** Support local LLMs using Ollama's new OpenAI-Compatible server: 
+     simply specify `chat_model="ollama/mistral"`. See [release notes](https://github.com/langroid/langroid/releases/tag/0.1.193).
+  - **0.1.183:** Added Chainlit support via [callbacks](https://github.com/langroid/langroid/blob/main/langroid/agent/callbacks/chainlit.py). 
+   See [examples](https://github.com/langroid/langroid/tree/main/examples/chainlit).
+- **Jan 2024:**
+  - **0.1.175** 
+    - [Neo4jChatAgent](https://github.com/langroid/langroid/tree/main/langroid/agent/special/neo4j) to chat with a neo4j knowledge-graph.
+      (Thanks to [Mohannad](https://github.com/Mohannadcse)!). The agent uses tools to query the Neo4j schema and translate user queries to Cypher queries,
+      and the tool handler executes these queries, returning them to the LLM to compose
+      a natural language response (analogous to how `SQLChatAgent` works).
+      See example [script](https://github.com/langroid/langroid/tree/main/examples/kg-chat) using this Agent to answer questions about Python pkg dependencies.
+    - Support for `.doc` file parsing (in addition to `.docx`)
+    - Specify optional [`formatter` param](https://github.com/langroid/langroid/releases/tag/0.1.171) 
+      in `OpenAIGPTConfig` to ensure accurate chat formatting for local LLMs. 
+  - **[0.1.157](https://github.com/langroid/langroid/releases/tag/0.1.157):** `DocChatAgentConfig` 
+     has a new param: `add_fields_to_content`, to specify additional document fields to insert into 
+     the main `content` field, to help improve retrieval.
+  - **[0.1.156](https://github.com/langroid/langroid/releases/tag/0.1.156):** New Task control signals
+     PASS_TO, SEND_TO; VectorStore: Compute Pandas expression on documents; LanceRAGTaskCreator creates 3-agent RAG system with Query Planner, Critic and RAG Agent.
+- **Dec 2023:**
+  - **0.1.154:** (For details see release notes of [0.1.149](https://github.com/langroid/langroid/releases/tag/0.1.149)
+      and [0.1.154](https://github.com/langroid/langroid/releases/tag/0.1.154)). 
+    - `DocChatAgent`: Ingest Pandas dataframes and filtering.
+    - `LanceDocChatAgent` leverages `LanceDB` vector-db for efficient vector search
+     and full-text search and filtering.
+    - Improved task and multi-agent control mechanisms
+    - `LanceRAGTaskCreator` to create a 2-agent system consisting of a `LanceFilterAgent` that
+      decides a filter and rephrase query to send to a RAG agent.
+  - **[0.1.141](https://github.com/langroid/langroid/releases/tag/0.1.141):**
+    API Simplifications to reduce boilerplate:
+    auto-select an available OpenAI model (preferring gpt-4-turbo), simplifies defaults.
+    Simpler `Task` initialization with default `ChatAgent`.
 - **Nov 2023:**
-  - **0.1.126:** OpenAIAssistant agent: Caching Support. See [release notes](https://github.com/langroid/langroid/releases/tag/0.1.126).
+  - **[0.1.126](https://github.com/langroid/langroid/releases/tag/0.1.126):**
+     OpenAIAssistant agent: Caching Support. 
   - **0.1.117:** Support for OpenAI Assistant API tools: Function-calling, 
     Code-intepreter, and Retriever (RAG), file uploads. These work seamlessly 
     with Langroid's task-orchestration.
@@ -283,6 +369,8 @@ See [this test](tests/main/test_recipient_tool.py) for example usage.
 Suppose you want to extract structured information about the key terms 
 of a commercial lease document. You can easily do this with Langroid using a two-agent system,
 as we show in the [langroid-examples](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py) repo.
+(See [this script](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat-multi-extract-local.py)
+for a version with the same functionality using a local Mistral-7b model.)
 The demo showcases just a few of the many features of Langroid, such as:
 - Multi-agent collaboration: `LeaseExtractor` is in charge of the task, and its LLM (GPT4) generates questions 
 to be answered by the `DocAgent`.
@@ -299,7 +387,9 @@ Here is what it looks like in action
 
 
 # :zap: Highlights
-
+(For a more up-to-date list see the 
+[release](https://github.com/langroid/langroid?tab=readme-ov-file#fire-updatesreleases) 
+section above)
 - **Agents as first-class citizens:** The [Agent](https://langroid.github.io/langroid/reference/agent/base/#langroid.agent.base.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.
@@ -353,6 +443,15 @@ install Langroid like this:
 ```bash
 pip install langroid[hf-embeddings]
 ```
+If using `zsh` (or similar shells), you may need to escape the square brackets, e.g.:
+```
+pip install langroid\[hf-embeddings\]
+```
+or use quotes:
+```
+pip install "langroid[hf-embeddings]"
+```
+
 
 <details>
 <summary><b>Optional Installs for using SQL Chat with a PostgreSQL DB </b></summary>
@@ -460,8 +559,8 @@ provides more information, and you can set each environment variable as follows:
 - `AZURE_OPENAI_API_BASE` from the value of `ENDPOINT`, typically looks like `https://your.domain.azure.com`.
 - For `AZURE_OPENAI_API_VERSION`, you can use the default value in `.env-template`, and latest version can be found [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/whats-new#azure-openai-chat-completion-general-availability-ga)
 - `AZURE_OPENAI_DEPLOYMENT_NAME` is the name of the deployed model, which is defined by the user during the model setup 
-- `AZURE_OPENAI_MODEL_NAME` GPT-3.5-Turbo or GPT-4 model names that you chose when you setup your Azure OpenAI account.
-
+- `AZURE_OPENAI_MODEL_NAME` Azure OpenAI allows specific model names when you select the model for your deployment. You need to put precisly the exact model name that was selected. For example, GPT-3.5 (should be `gpt-35-turbo-16k` or `gpt-35-turbo`) or GPT-4 (should be `gpt-4-32k` or `gpt-4`).
+- `AZURE_OPENAI_MODEL_VERSION` is required if `AZURE_OPENAI_MODEL_NAME = gpt=4`, which will assist Langroid to determine the cost of the model  
 </details>
 
 ---
@@ -520,19 +619,15 @@ All of these can be run in a Colab notebook:
 <summary> <b> Direct interaction with OpenAI LLM </b> </summary>
 
 ```python
-from langroid.language_models.openai_gpt import ( 
-        OpenAIGPTConfig, OpenAIChatModel, OpenAIGPT,
-)
-from langroid.language_models.base import LLMMessage, Role
+import langroid.language_models as lm
 
-cfg = OpenAIGPTConfig(chat_model=OpenAIChatModel.GPT4)
-
-mdl = OpenAIGPT(cfg)
+mdl = lm.OpenAIGPT()
 
 messages = [
-  LLMMessage(content="You are a helpful assistant",  role=Role.SYSTEM), 
-  LLMMessage(content="What is the capital of Ontario?",  role=Role.USER),
+  lm.LLMMessage(content="You are a helpful assistant",  role=lm.Role.SYSTEM), 
+  lm.LLMMessage(content="What is the capital of Ontario?",  role=lm.Role.USER),
 ]
+
 response = mdl.chat(messages, max_tokens=200)
 print(response.message)
 ```
@@ -543,11 +638,11 @@ print(response.message)
 Local model: if model is served at `http://localhost:8000`:
 
 ```python
-cfg = OpenAIGPTConfig(
+cfg = lm.OpenAIGPTConfig(
   chat_model="local/localhost:8000", 
   chat_context_length=4096
 )
-mdl = OpenAIGPT(cfg)
+mdl = lm.OpenAIGPT(cfg)
 # now interact with it as above, or create an Agent + Task as shown below.
 ```
 
@@ -574,21 +669,14 @@ pip install langroid[litellm]
 <summary> <b> Define an agent, set up a task, and run it </b> </summary>
 
 ```python
-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, # no vector store
-)
-agent = ChatAgent(config)
+import langroid as lr
+
+agent = lr.ChatAgent()
+
 # get response from agent's LLM, and put this in an interactive loop...
 # 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 = lr.Task(agent, name="Bot") 
 task.run() # ... a loop seeking response from LLM or User at each turn
 ```
 </details>
@@ -597,26 +685,17 @@ task.run() # ... a loop seeking response from LLM or User at each turn
 <summary><b> Three communicating agents </b></summary>
 
 A toy numbers game, where when given a number `n`:
-- `repeater_agent`'s LLM simply returns `n`,
-- `even_agent`'s LLM returns `n/2` if `n` is even, else says "DO-NOT-KNOW"
-- `odd_agent`'s LLM returns `3*n+1` if `n` is odd, else says "DO-NOT-KNOW"
+- `repeater_task`'s LLM simply returns `n`,
+- `even_task`'s LLM returns `n/2` if `n` is even, else says "DO-NOT-KNOW"
+- `odd_task`'s LLM returns `3*n+1` if `n` is odd, else says "DO-NOT-KNOW"
 
-First define the 3 agents, and set up their tasks with instructions:
+Each of these `Task`s automatically configures a default `ChatAgent`.
 
 ```python
+import langroid as lr
 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,
+
+repeater_task = lr.Task(
     name = "Repeater",
     system_message="""
     Your job is to repeat whatever number you receive.
@@ -624,9 +703,8 @@ repeater_task = Task(
     llm_delegate=True, # LLM takes charge of task
     single_round=False, 
 )
-even_agent = ChatAgent(config)
-even_task = Task(
-    even_agent,
+
+even_task = lr.Task(
     name = "EvenHandler",
     system_message=f"""
     You will be given a number. 
@@ -636,9 +714,7 @@ even_task = Task(
     single_round=True,  # task done after 1 step() with valid response
 )
 
-odd_agent = ChatAgent(config)
-odd_task = Task(
-    odd_agent,
+odd_task = lr.Task(
     name = "OddHandler",
     system_message=f"""
     You will be given a number n. 
@@ -677,8 +753,9 @@ First define the tool using Langroid's `ToolMessage` class:
 
 
 ```python
-from langroid.agent.tool_message import ToolMessage
-class ProbeTool(ToolMessage):
+import langroid as lr
+
+class ProbeTool(lr.agent.ToolMessage):
   request: str = "probe" # specifies which agent method handles this tool
   purpose: str = """
         To find how many numbers in my list are less than or equal to  
@@ -691,9 +768,8 @@ Then define a `SpyGameAgent` as a subclass of `ChatAgent`,
 with a method `probe` that handles this tool:
 
 ```python
-from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
-class SpyGameAgent(ChatAgent):
-  def __init__(self, config: ChatAgentConfig):
+class SpyGameAgent(lr.ChatAgent):
+  def __init__(self, config: lr.ChatAgentConfig):
     super().__init__(config)
     self.numbers = [3, 4, 8, 11, 15, 25, 40, 80, 90]
 
@@ -705,13 +781,9 @@ class SpyGameAgent(ChatAgent):
 We then instantiate the agent and enable it to use and respond to the tool:
 
 ```python
-from langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig
 spy_game_agent = SpyGameAgent(
-    ChatAgentConfig(
+    lr.ChatAgentConfig(
         name="Spy",
-        llm = OpenAIGPTConfig(
-            chat_model=OpenAIChatModel.GPT4,
-        ),
         vecdb=None,
         use_tools=False, #  don't use Langroid native tool
         use_functions_api=True, # use OpenAI function-call API
@@ -753,7 +825,9 @@ Then define the `LeaseMessage` tool as a subclass of Langroid's `ToolMessage`.
 Note the tool has a required argument `terms` of type `Lease`:
 
 ```python
-class LeaseMessage(ToolMessage):
+import langroid as lr
+
+class LeaseMessage(lr.agent.ToolMessage):
     request: str = "lease_info"
     purpose: str = """
         Collect information about a Commercial Lease.
@@ -765,7 +839,7 @@ Then define a `LeaseExtractorAgent` with a method `lease_info` that handles this
 instantiate the agent, and enable it to use and respond to this tool:
 
 ```python
-class LeaseExtractorAgent(ChatAgent):
+class LeaseExtractorAgent(lr.ChatAgent):
     def lease_info(self, message: LeaseMessage) -> str:
         print(
             f"""
@@ -775,13 +849,7 @@ class LeaseExtractorAgent(ChatAgent):
         )
         return json.dumps(message.terms.dict())
     
-lease_extractor_agent = LeaseExtractorAgent(
-  ChatAgentConfig(
-    llm=OpenAIGPTConfig(),
-    use_functions_api=False,
-    use_tools=True,
-  )
-)
+lease_extractor_agent = LeaseExtractorAgent()
 lease_extractor_agent.enable_message(LeaseMessage)
 ```
 
@@ -800,18 +868,16 @@ First create a `DocChatAgentConfig` instance, with a
 `doc_paths` field that specifies the documents to chat with.
 
 ```python
-from langroid.agent.doc_chat_agent import DocChatAgentConfig
-from langroid.vector_store.lancedb import LanceDBConfig
+import langroid as lr
+from langroid.agent.special import DocChatAgentConfig, DocChatAgent
+
 config = DocChatAgentConfig(
   doc_paths = [
     "https://en.wikipedia.org/wiki/Language_model",
     "https://en.wikipedia.org/wiki/N-gram_language_model",
     "/path/to/my/notes-on-language-models.txt",
-  ]
-  llm = OpenAIGPTConfig(
-    chat_model=OpenAIChatModel.GPT4,
-  ),
-  vecdb=LanceDBConfig(),
+  ],
+  vecdb=lr.vector_store.LanceDBConfig(),
 )
 ```
 
@@ -822,12 +888,11 @@ agent = DocChatAgent(config)
 ```
 Then we can either ask the agent one-off questions,
 ```python
-agent.chat("What is a language model?")
+agent.llm_response("What is a language model?")
 ```
 or wrap it in a `Task` and run an interactive loop with the user:
 ```python
-from langroid.task import Task
-task = Task(agent)
+task = lr.Task(agent)
 task.run()
 ```
 
@@ -847,9 +912,8 @@ executes the code and returns the answer.
 Here is how you can do this:
 
 ```python
-from langroid.agent.special.table_chat_agent import TableChatAgent, TableChatAgentConfig
-from langroid.agent.task import Task
-from langroid.language_models.openai_gpt import OpenAIChatModel, OpenAIGPTConfig
+import langroid as lr
+from langroid.agent.special import TableChatAgent, TableChatAgentConfig
 ```
 
 Set up a `TableChatAgent` for a data file, URL or dataframe
@@ -860,17 +924,14 @@ dataset =  "https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quali
 # or dataset = pd.read_csv("/path/to/my/data.csv")
 agent = TableChatAgent(
     config=TableChatAgentConfig(
-        data=dataset,  
-        llm=OpenAIGPTConfig(
-            chat_model=OpenAIChatModel.GPT4,
-        ),
+        data=dataset,
     )
 )
 ```
 Set up a task, and ask one-off questions like this: 
 
 ```python
-task = Task(
+task = lr.Task(
   agent, 
   name = "DataAssistant",
   default_human_response="", # to avoid waiting for user input
@@ -884,7 +945,7 @@ print(result.content)
 Or alternatively, set up a task and run it in an interactive loop with the user:
 
 ```python
-task = Task(agent, name="DataAssistant")
+task = lr.Task(agent, name="DataAssistant")
 task.run()
 ```