Merge pull request #317 from harishmohanraj/main

[Docs] Fix Broken Links and Improve Example Formatting in Docstrings

.devcontainer/dev/Dockerfile

@@ -30,10 +30,13 @@ RUN sudo pip install --upgrade pip && \
 # Install pre-commit hooks
 RUN pre-commit install
 
-# Setup Mintlify for the documentation website
+# Install Python packages for documentation
 RUN sudo pip install pydoc-markdown pyyaml termcolor nbclient
-RUN cd website
+
+# Install npm packages for documentation
+WORKDIR /home/autogen/ag2/website
 RUN npm install
+WORKDIR /home/autogen/ag2
 
 RUN arch=$(arch | sed s/aarch64/arm64/ | sed s/x86_64/amd64/) && \
     wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.5.23/quarto-1.5.23-linux-${arch}.tar.gz && \

.muffet-excluded-links.txt

@@ -1,8 +1,16 @@
+http://localhost
 linkedin.com
 x.com
+twitter.com
 example.com
 rapidapi.com
-https://platform.openai.com/docs/
+https://platform.openai.com
+https://openai.com
+https://code.visualstudio.com/docs/devcontainers/containers
+https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023
+https://www.llama.com/docs/how-to-guides/prompting/
+https://azure.microsoft.com/en-us/get-started/azure-portal
+https://github.com/pgvector/pgvector?tab=readme-ov-file
 https://github.com/ag2ai/ag2/blob/b1adac515931bf236ac59224269eeec683a162ba/test/oai/test_client.py
 https://github.com/ag2ai/ag2/blob/main/notebook/contributing.md
 https://github.com/openai/openai-python/blob/d231d1fa783967c1d3a1db3ba1b52647fff148ac/src/openai/resources/completions.py

autogen/agentchat/chat.py

@@ -164,7 +164,7 @@ def initiate_chats(chat_queue: list[dict[str, Any]]) -> list[ChatResult]:
         chat_queue (List[Dict]): A list of dictionaries containing the information about the chats.
 
         Each dictionary should contain the input arguments for
-        [`ConversableAgent.initiate_chat`](/docs/reference/agentchat/conversable_agent#initiate_chat).
+        [`ConversableAgent.initiate_chat`](/docs/reference/agentchat/conversable_agent#initiate-chat).
         For example:
             - `"sender"` - the sender agent.
             - `"recipient"` - the recipient agent.

autogen/agentchat/contrib/capabilities/vision_capability.py

@@ -141,22 +141,24 @@ def process_last_received_message(self, content: Union[str, list[dict]]) -> str:
             (Content is a string without an image, remains unchanged.)
 
         - Input as String, with image location:
-            content = "What's weather in this cool photo: <img http://example.com/photo.jpg>"
-            Output: "What's weather in this cool photo: <img http://example.com/photo.jpg> in case you can not see, the caption of this image is:
+            content = "What's weather in this cool photo: `<img http://example.com/photo.jpg>`"
+            Output: "What's weather in this cool photo: `<img http://example.com/photo.jpg>` in case you can not see, the caption of this image is:
             A beautiful sunset over the mountains\n"
             (Caption added after the image)
 
         - Input as List with Text Only:
-            content = [{"type": "text", "text": "Here's an interesting fact."}]
+            content = `[{"type": "text", "text": "Here's an interesting fact."}]`
             Output: "Here's an interesting fact."
             (No images in the content, it remains unchanged.)
 
         - Input as List with Image URL:
+            ```python
             content = [
                 {"type": "text", "text": "What's weather in this cool photo:"},
                 {"type": "image_url", "image_url": {"url": "http://example.com/photo.jpg"}}
             ]
-            Output: "What's weather in this cool photo: <img http://example.com/photo.jpg> in case you can not see, the caption of this image is:
+            ```
+            Output: "What's weather in this cool photo: `<img http://example.com/photo.jpg>` in case you can not see, the caption of this image is:
             A beautiful sunset over the mountains\n"
             (Caption added after the image)
         """

autogen/agentchat/contrib/graph_rag/graph_rag_capability.py

@@ -20,6 +20,7 @@ class GraphRagCapability(AgentCapability):
     3. generate answers from retrieved information and send messages back.
 
     For example,
+    ```python
     graph_query_engine = GraphQueryEngine(...)
     graph_query_engine.init_db([Document(doc1), Document(doc2), ...])
 
@@ -50,7 +51,7 @@ class GraphRagCapability(AgentCapability):
             #   - Hugo Weaving',
             #   'role': 'user_proxy'},
         # ...)
-
+    ```
     """
 
     def __init__(self, query_engine: GraphQueryEngine):

autogen/agentchat/contrib/img_utils.py

@@ -112,7 +112,7 @@ def llava_formatter(prompt: str, order_image_tokens: bool = False) -> tuple[str,
     Formats the input prompt by replacing image tags and returns the new prompt along with image locations.
 
     Parameters:
-        - prompt (str): The input string that may contain image tags like <img ...>.
+        - prompt (str): The input string that may contain image tags like `<img ...>`.
         - order_image_tokens (bool, optional): Whether to order the image tokens with numbers.
             It will be useful for GPT-4V. Defaults to False.
 
@@ -194,7 +194,7 @@ def gpt4v_formatter(prompt: str, img_format: str = "uri") -> list[Union[str, dic
     Formats the input prompt by replacing image tags and returns a list of text and images.
 
     Args:
-        - prompt (str): The input string that may contain image tags like <img ...>.
+        - prompt (str): The input string that may contain image tags like `<img ...>`.
         - img_format (str): what image format should be used. One of "uri", "url", "pil".
 
     Returns:
@@ -293,24 +293,28 @@ def message_formatter_pil_to_b64(messages: list[dict]) -> list[dict]:
                     'image_url' key converted to base64 encoded data URIs.
 
     Example Input:
+        ```python
         [
             {'content': [{'type': 'text', 'text': 'You are a helpful AI assistant.'}], 'role': 'system'},
             {'content': [
-                {'type': 'text', 'text': "What's the breed of this dog here? \n"},
+                {'type': 'text', 'text': "What's the breed of this dog here?"},
                 {'type': 'image_url', 'image_url': {'url': a PIL.Image.Image}},
                 {'type': 'text', 'text': '.'}],
             'role': 'user'}
         ]
+        ```
 
     Example Output:
+        ```python
         [
             {'content': [{'type': 'text', 'text': 'You are a helpful AI assistant.'}], 'role': 'system'},
             {'content': [
-                {'type': 'text', 'text': "What's the breed of this dog here? \n"},
+                {'type': 'text', 'text': "What's the breed of this dog here?"},
                 {'type': 'image_url', 'image_url': {'url': a B64 Image}},
                 {'type': 'text', 'text': '.'}],
             'role': 'user'}
         ]
+        ```
     """
     new_messages = []
     for message in messages:

autogen/agentchat/contrib/vectordb/chromadb.py

@@ -39,11 +39,11 @@ def __init__(
         Args:
             client: chromadb.Client | The client object of the vector database. Default is None.
                 If provided, it will use the client object directly and ignore other arguments.
-            path: str | The path to the vector database. Default is `tmp/db`. The default was `None` for version <=0.2.24.
+            path: str | The path to the vector database. Default is `tmp/db`. The default was `None` for version `<=0.2.24`.
             embedding_function: Callable | The embedding function used to generate the vector representation
                 of the documents. Default is None, SentenceTransformerEmbeddingFunction("all-MiniLM-L6-v2") will be used.
             metadata: dict | The metadata of the vector database. Default is None. If None, it will use this
-                setting: {"hnsw:space": "ip", "hnsw:construction_ef": 30, "hnsw:M": 32}. For more details of
+                setting: `{"hnsw:space": "ip", "hnsw:construction_ef": 30, "hnsw:M": 32}`. For more details of
                 the metadata, please refer to [distances](https://github.com/nmslib/hnswlib#supported-distances),
                 [hnsw](https://github.com/chroma-core/chroma/blob/566bc80f6c8ee29f7d99b6322654f32183c368c4/chromadb/segment/impl/vector/local_hnsw.py#L184),
                 and [ALGO_PARAMS](https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md).
@@ -248,7 +248,7 @@ def retrieve_docs(
             collection_name: str | The name of the collection. Default is None.
             n_results: int | The number of relevant documents to return. Default is 10.
             distance_threshold: float | The threshold for the distance score, only distance smaller than it will be
-                returned. Don't filter with it if < 0. Default is -1.
+                returned. Don't filter with it if `< 0`. Default is -1.
             kwargs: Dict | Additional keyword arguments.
 
         Returns:
@@ -279,6 +279,7 @@ def _chroma_get_results_to_list_documents(data_dict) -> list[Document]:
             List[Document] | The list of Document.
 
         Example:
+            ```python
             data_dict = {
                 "key1s": [1, 2, 3],
                 "key2s": ["a", "b", "c"],
@@ -291,6 +292,7 @@ def _chroma_get_results_to_list_documents(data_dict) -> list[Document]:
                 {"key1": 2, "key2": "b", "key4": "y"},
                 {"key1": 3, "key2": "c", "key4": "z"},
             ]
+            ```
         """
 
         results = []

autogen/agentchat/contrib/vectordb/pgvectordb.py

@@ -606,7 +606,7 @@ def __init__(
                 Models can be chosen from:
                 https://huggingface.co/models?library=sentence-transformers
             metadata: dict | The metadata of the vector database. Default is None. If None, it will use this
-                setting: {"hnsw:space": "ip", "hnsw:construction_ef": 30, "hnsw:M": 16}. Creates Index on table
+                setting: `{"hnsw:space": "ip", "hnsw:construction_ef": 30, "hnsw:M": 16}`. Creates Index on table
                 using hnsw (embedding vector_l2_ops) WITH (m = hnsw:M) ef_construction = "hnsw:construction_ef".
                 For more info: https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw
         Returns:
@@ -917,7 +917,7 @@ def retrieve_docs(
             collection_name: str | The name of the collection. Default is None.
             n_results: int | The number of relevant documents to return. Default is 10.
             distance_threshold: float | The threshold for the distance score, only distance smaller than it will be
-                returned. Don't filter with it if < 0. Default is -1.
+                returned. Don't filter with it if `< 0`. Default is -1.
             kwargs: Dict | Additional keyword arguments.
 
         Returns:

autogen/agentchat/contrib/vectordb/qdrant.py

@@ -56,7 +56,7 @@ def __init__(
                                       Defaults to None.
             **kwargs: Additional options to pass to fastembed.TextEmbedding
         Raises:
-            ValueError: If the model_name is not in the format <org>/<model> e.g. BAAI/bge-small-en-v1.5.
+            ValueError: If the model_name is not in the format `<org>/<model>` e.g. BAAI/bge-small-en-v1.5.
         """
         try:
             from fastembed import TextEmbedding
@@ -229,7 +229,7 @@ def retrieve_docs(
             collection_name: str | The name of the collection. Default is None.
             n_results: int | The number of relevant documents to return. Default is 10.
             distance_threshold: float | The threshold for the distance score, only distance smaller than it will be
-                returned. Don't filter with it if < 0. Default is 0.
+                returned. Don't filter with it if `< 0`. Default is 0.
             kwargs: Dict | Additional keyword arguments.
 
         Returns:

autogen/agentchat/contrib/vectordb/utils.py

@@ -78,6 +78,7 @@ def chroma_results_to_query_results(data_dict: dict[str, list[list[Any]]], speci
         special_key.
 
     Example:
+        ```python
         data_dict = {
             "key1s": [[1, 2, 3], [4, 5, 6], [7, 8, 9]],
             "key2s": [["a", "b", "c"], ["c", "d", "e"], ["e", "f", "g"]],
@@ -103,6 +104,7 @@ def chroma_results_to_query_results(data_dict: dict[str, list[list[Any]]], speci
                 ({"key1": 9, "key2": "g", "key4": "6"}, 0.9),
             ],
         ]
+        ```
     """
 
     keys = [

autogen/agentchat/conversable_agent.py

@@ -1048,7 +1048,7 @@ def initiate_chat(
             silent (bool or None): (Experimental) whether to print the messages for this conversation. Default is False.
             cache (AbstractCache or None): the cache client to be used for this conversation. Default is None.
             max_turns (int or None): the maximum number of turns for the chat between the two agents. One turn means one conversation round trip. Note that this is different from
-                [max_consecutive_auto_reply](#max-consecutive-auto-reply) which is the maximum number of consecutive auto replies; and it is also different from [max_rounds in GroupChat](./groupchat#groupchat-objects) which is the maximum number of rounds in a group chat session.
+                [max_consecutive_auto_reply](#max-consecutive-auto-reply) which is the maximum number of consecutive auto replies; and it is also different from [max_rounds in GroupChat](./groupchat) which is the maximum number of rounds in a group chat session.
                 If max_turns is set to None, the chat will continue until a termination condition is met. Default is None.
             summary_method (str or callable): a method to get a summary from the chat. Default is DEFAULT_SUMMARY_METHOD, i.e., "last_msg".
 
@@ -1376,7 +1376,7 @@ def initiate_chats(self, chat_queue: list[dict[str, Any]]) -> list[ChatResult]:
 
         Args:
             chat_queue (List[Dict]): a list of dictionaries containing the information of the chats.
-                Each dictionary should contain the input arguments for [`initiate_chat`](conversable_agent#initiate_chat)
+                Each dictionary should contain the input arguments for [`initiate_chat`](conversable_agent#initiate-chat)
 
         Returns: a list of ChatResult objects corresponding to the finished chats in the chat_queue.
         """