ugorsahin · ugorsahin · Mar 18, 2024 · Mar 16, 2024 · Mar 16, 2024 · Mar 16, 2024
diff --git a/.gitignore b/.gitignore
@@ -32,4 +32,7 @@ MANIFEST
 _build
 
 # CircleCI
-artifacts
+artifacts
+
+# Testing
+talkingheads_userprofile
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -0,0 +1,21 @@
+## 0.5.0 (2024-03-18)
+
+### Feat
+
+- **is_url_check_filetype**: new functions to check filetype and if the string is url
+- **lechat**: Mistral Le Chat is automated
+- **gemini_multimodal**: It is possible to upload image to Gemini
+- **image**: Implementation of image upload feature
+- **multiagent**: First commit of Multiagent subpackage including Conversation
+- **reset_thread**: now it is possible to reset chat, disabled model switch
+
+### Fix
+
+- **import**: Changed init file
+- **logging**: import logging removed
+- **object_markers**: Fixed old markers and new file format
+- **init**: Initialization fixes
+- **logging_and_driver_arguments**: It is now possible to pass driver arguments as dictionary
+- **logging_interacting**: Logging changed to instance based logger and fixed a bug in interaction
+- **claude**: Fixed a response error
+- **logging**: uses it's own logging
diff --git a/README.md b/README.md
@@ -20,20 +20,23 @@
     <img src='https://github.com/ugorsahin/TalkingHeads/actions/workflows/codeql.yml/badge.svg' alt='CodeQL Status' />
   </a>
   <a href="https://codecov.io/gh/ugorsahin/TalkingHeads" > 
-    <img src="https://codecov.io/gh/ugorsahin/TalkingHeads/graph/badge.svg?token=YPXKNXSZAD"/> 
+    <img src="https://badgen.net/codecov/c/github/ugorsahin/talkingheads"/> 
   </a>
-  <a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
+  <a href="https://github.com/astral-sh/ruff"><img alt="Code style: black" src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json"></a>
 </p>
 
 Welcome to TalkingHeads! 💬
 
-TalkingHeads is a versatile Python library that serves as an interface for seamless communication with ChatGPT, Claude, Copilot, Gemini, HuggingChat, and Pi  🤖
+TalkingHeads is a Python library that serves as an interface for seamless communication with ChatGPT, Claude, Copilot, Gemini, LeChat, HuggingChat, and Pi  🤖
 
-By leveraging the power of browser automation, this library enables users to effortlessly interact with online LLM tools, providing a streamlined and automated approach to generate responses. 🚀✨
+By leveraging the power of browser automation, this library enables users to effortlessly interact with online chat agents 🚀✨
+
+You can utilize more than one agent by using multiagent module, and improve your workflow with an ensemble of models!
 
 # Prerequisites 📋
 
-Before you begin, please ensure that you have Chrome installed on your system. To successfully pass the Cloudflare robot test, it is necessary to have undetected-chrome. 🌐🔒
+- Install Chrome
+- Register to the provider you would like to use (or not, and use Pi!)
 
 ## Installation
 
@@ -54,34 +57,37 @@ from talkingheads import PiClient
 
 chathead = PiClient()
 
-answer = chathead.interact("Hello, how are you today")
+response = chathead.interact("Hello, how are you today")
 
-print(answer)
+print(response)
 ```
 
 ## Features
-
-Features | Gemini | Claude | Copilot | HuggingChat | ChatGPT | Pi |
-|--------|------|--------|---------|-------------|---------|----|
-Use without login | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ |
-Login* | ➖ | ➖ | ➖ | ✅ | ✅ | ➖ |
-Interact | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
-New Chat | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
-Regenerate Response | ✅ | ✅ | ❌  | ❌ | ✅ | ❌ |
-Set custom interactions | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |
-Search Web | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ |
-Plugins | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ |
-Switch Model | ❌ | ❌ | ✅** | ✅ | ✅ | ✅ |
+Features            | Claude | ChatGPT | Copilot | Gemini | LeChat | HuggingChat | Pi |
+|-------------------|--------|---------|---------|--------|--------|-------------|----|
+Use without login   | ❌     | ❌      | ✅      | ❌     |  ❌    | ❌          | ✅ |
+Login*              | ➖     | ✅      | ➖      | ➖     |  ✅    | ✅          | ➖ |
+Interact            | ✅     | ✅      | ✅      | ✅     |  ✅    | ✅          | ✅ |
+New Chat            | ✅     | ✅      | ✅      | ✅     |  ✅    | ✅          | ✅ |
+Regenerate Response | ✅     | ✅      | ❌      | ✅     |  ❌    | ❌          | ❌ |
+Custom Interactions | ❌     | ✅      | ❌      | ❌     |  ❌    | ❌          | ❌ |
+Search Web          | ❌     | ❌      | ✅      | ❌     |  ❌    | ✅          | ❌ |
+Plugins             | ❌     | ❌      | ✅      | ❌     |  ❌    | ❌          | ❌ |
+Switch Model        | ❌     | ✅      | ✅**    | ❌     |  ✅    | ✅          | ✅ |
+Multimodal (Visual) | ✅     | ➖***   | ✅      | ✅     |  ❌    | ❌          | ❌ |
 
 ✅ (Auto) Save the conversation as csv, h5, html, json, orc, pkl, xlsx, xml
 
 - ✅ : Functionality exists and implemented
 - ❌ : Functionality does not exist
 - ➖ : Fuctionality exists but not implemented
 
-\* The first time login is manually done for Gemini, Claude and Copilot. Check documentation for first time setup. Please take a look at [FAQ](FAQ.md) to set up.
+\* You should use a user profile and login manually to use Gemini, Claude and Copilot.Please take a look at documentation and [FAQ](FAQ.md) to set up a user profile.
+
 \*\* The modes of Copilot (Creative, Balanced and Precise) are accessible with model switch. However, it is unclear if they are different models.
 
+\*\*\* ChatGPT has multimodality, but only for premium users, donate me a premium account if you need that to be implemented!
+
 ## Issues & Contribution
 
 Feel free to dive in, share your knowledge, and collaborate. I would be happy to answer any questions or accept your contributions. Let me know in issues if you need anything.
@@ -94,15 +100,15 @@ Please indicate your issue with a tag enclosed by square brackets: [FEATURE], [B
 You can still run your code to connect ChatGPT, follow the below tutorial
 
 ```bash
-export OPENAI_UNAME=<your@email>
-export OPENAI_PWD=><password>
+export ChatGPT_UNAME=<your@email>
+export ChatGPT_PWD=><password>
 ```
 ```python
 from talkingheads import ChatGPTClient
 
 chathead = ChatGPTClient()
 
-answer = chathead.interact("Hello, how are you today")
+response = chathead.interact("Hello, how are you today")
 
-print(answer)
+print(response)
 ```
diff --git a/docs/_static/custom_style.css b/docs/_static/custom_style.css
@@ -0,0 +1,3 @@
+.wy-nav-content {
+    max-width: 900px;
+}
diff --git a/docs/conf.py b/docs/conf.py
@@ -11,28 +11,37 @@
 sys.path.insert(0, os.path.abspath("../src/"))
 
 project = "TalkingHeads"
-copyright = "2023, Ugur Sahin"
+copyright = "2024, Ugur Sahin"
 author = "Ugur Sahin"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
 extensions = [
+    "sphinx_markdown_tables",
+    "sphinx.ext.napoleon",
     "sphinx.ext.autodoc",
     "sphinx.ext.autosummary",
     "sphinx.ext.doctest",
-    "sphinx.ext.napoleon",
     "myst_parser",
 ]
 
 templates_path = ["_templates"]
 exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
+# Markdown support
+source_parsers = {
+    '.md': 'recommonmark.parser.CommonMarkParser',
+}
+
+source_suffix = ['.rst', '.md']
+
 # -- Options for HTML output -------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
 
 html_theme = "sphinx_rtd_theme"
 html_static_path = ["_static"]
+html_css_files = ['custom_style.css']
 
 add_module_names = True
 autodoc_member_order = "groupwise"

diff --git a/docs/index.rst b/docs/index.rst
@@ -11,8 +11,10 @@ By leveraging the power of browser automation, this library enables users to int
    :maxdepth: 2
    :caption: Contents:
 
-   tutorial/features
-   tutorial/getting_started.md
+   tutorial/features.md
+   tutorial/getting_started
+   tutorial/multiagent
+   tutorial/conversation
    source/talkingheads
 
 Indices and tables

diff --git a/docs/source/talkingheads.model_library.rst b/docs/source/talkingheads.model_library.rst
@@ -1,61 +1,51 @@
-talkingheads.model\_library package
+talkingheads.model\_library
 ===================================
 
-Submodules
-----------
-
-talkingheads.model\_library.Gemini module
----------------------------------------
+talkingheads.model\_library.chatgpt
+------------------------------------------
 
-.. automodule:: talkingheads.model_library.Gemini
+.. automodule:: talkingheads.model_library.chatgpt
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.model\_library.chatgpt module
-------------------------------------------
+talkingheads.model\_library.claude
+-----------------------------------------
 
-.. automodule:: talkingheads.model_library.chatgpt
+.. automodule:: talkingheads.model_library.claude
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.model\_library.huggingchat module
-----------------------------------------------
+talkingheads.model\_library.copilot
+------------------------------------------
 
-.. automodule:: talkingheads.model_library.huggingchat
+.. automodule:: talkingheads.model_library.copilot
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.model\_library.pi module
--------------------------------------
+talkingheads.model\_library.gemini
+-----------------------------------------
 
-.. automodule:: talkingheads.model_library.pi
+.. automodule:: talkingheads.model_library.gemini
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.model\_library.copilot module
--------------------------------------
+talkingheads.model\_library.huggingchat
+----------------------------------------------
 
-.. automodule:: talkingheads.model_library.copilot
+.. automodule:: talkingheads.model_library.huggingchat
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.model\_library.claude module
--------------------------------------
+talkingheads.model\_library.lechat
+-----------------------------------------
 
-.. automodule:: talkingheads.model_library.claude
+.. automodule:: talkingheads.model_library.lechat
    :members:
-   :undoc-members:
    :show-inheritance:
 
-Module contents
----------------
+talkingheads.model\_library.pi
+-------------------------------------
 
-.. automodule:: talkingheads.model_library
+.. automodule:: talkingheads.model_library.pi
    :members:
-   :undoc-members:
-   :show-inheritance:
+   :show-inheritance:
diff --git a/docs/source/talkingheads.multiagent.rst b/docs/source/talkingheads.multiagent.rst
@@ -0,0 +1,7 @@
+talkingheads.multiagent
+===============================
+
+.. automodule:: talkingheads.multiagent
+   :members:
+   :undoc-members:
+   :show-inheritance:
diff --git a/docs/source/talkingheads.rst b/docs/source/talkingheads.rst
@@ -1,5 +1,5 @@
-talkingheads package
-====================
+talkingheads API documentation
+==============================
 
 Subpackages
 -----------
@@ -8,38 +8,25 @@ Subpackages
    :maxdepth: 4
 
    talkingheads.model_library
+   talkingheads.multiagent
 
-Submodules
-----------
-
-talkingheads.base\_browser module
+talkingheads.base\_browser
 ---------------------------------
 
 .. automodule:: talkingheads.base_browser
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.object\_map module
+talkingheads.object\_map
 -------------------------------
 
 .. automodule:: talkingheads.object_map
    :members:
-   :undoc-members:
    :show-inheritance:
 
-talkingheads.utils module
+talkingheads.utils
 -------------------------
 
 .. automodule:: talkingheads.utils
    :members:
-   :undoc-members:
-   :show-inheritance:
-
-Module contents
----------------
-
-.. automodule:: talkingheads
-   :members:
-   :undoc-members:
    :show-inheritance:
diff --git a/docs/tutorial/conversation.rst b/docs/tutorial/conversation.rst
@@ -0,0 +1,52 @@
+How to use Conversation
+=======================
+
+Conversation is a special case of multiagent interactions, where only two agents are involved. The configuration file for conversation is similar to the multiagent configuration, but a conversation only has two agents. The following example demonstrates an example:
+
+.. code-block:: python
+
+    conversation_head = Conversation('path/to/config.yaml')
+    interviewer = """Assume you are a researcher and will conduct a human cognition test.
+    Instruct the subject with the following instructions, one by one. Only ask for one instruction at a time.
+    Here are the instructions
+    1) Without further ado, just write the following: "Book."
+    2) Calculate 4x10.
+    3) Name three countries with the largest total area in North America.
+
+    Start by greeting the subject."""
+
+    candidate = (
+        "You accepted participating in a research study "
+        "and you will follow the instructions of the researchers."
+        "Answer with proper sentences."
+    )
+
+    responses = conversation_head.start_conversation(
+        intro_prompt_1=interviewer, intro_prompt_2=candidate
+    )
+    print(response[0]) # interviewer
+    print(response[1]) # candidate
+
+Output:
+
+.. code-block::
+
+    Greetings! Thank you for participating in our human cognition test. Let's begin with the first instruction:
+    Please write the word "Book."
+
+    Book
+
+.. code-block:: python
+
+    responses = conversation_head.continue_conversation()
+    print(response[0]) # interviewer
+    print(response[1]) # candidate
+
+Output:
+.. code-block::
+
+    Great job! Now, onto the second instruction:
+    Please calculate 4 multiplied by 10.
+
+    4 multiplied by 10 equals 40.
+