yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2025-11-03 11:20:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Multiline docstrings fix (#2130)

Browse Source 
* DOC FIX - Formatted Docstrings for the retrieve_user_proxy_agent.py and Added first single line for the class RetrieveUserProxyAgent.

* DOC FIX - Formatted Docstrings for  theinitiate_chats functiion of ChatResult class in  autogen/agentchat/chat.py

* Add vision capability (#2025)

* Add vision capability

* Configurate: description_prompt

* Print warning instead of raising issues for type

* Skip vision capability test if dependencies not installed

* Append "vision" to agent's system message when enabled VisionCapability

* GPT-4V notebook update with ConversableAgent

* Clean GPT-4V notebook

* Add vision capability test to workflow

* Lint import

* Update system message for vision capability

* Add a `custom_caption_func` to VisionCapability

* Add custom function example for vision capability

* Skip test Vision capability custom func

* GPT-4V notebook metadata to website

* Remove redundant files

* The custom caption function takes more inputs now

* Add a more complex example of custom caption func

* Remove trailing space

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Native tool call support for Mistral AI API and topic notebook. (#2135)

* Support for Mistral AI API and topic notebook.

* formatting

* formatting

* New conversational chess notebook using nested chats and tool use (#2137)

* add chess notebook

* update

* update

* Update notebook with figure

* Add example link

* redirect

* Clean up example format

* address gagan's comments

* update references

* fix links

* add webarena in samples (#2114)

* add webarena in samples/tools

* Update samples/tools/webarena/README.md

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Update samples/tools/webarena/README.md

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Update samples/tools/webarena/README.md

Co-authored-by: gagb <gagb@users.noreply.github.com>

* update installation instructions

* black formatting

* Update README.md

---------

Co-authored-by: gagb <gagb@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* context to kwargs (#2064)

* context to kwargs

* add tag

* add test

* text to kwargs

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Bump webpack-dev-middleware from 5.3.3 to 5.3.4 in /website (#2131)

Bumps [webpack-dev-middleware](https://github.com/webpack/webpack-dev-middleware) from 5.3.3 to 5.3.4.
- [Release notes](https://github.com/webpack/webpack-dev-middleware/releases)
- [Changelog](https://github.com/webpack/webpack-dev-middleware/blob/v5.3.4/CHANGELOG.md)
- [Commits](https://github.com/webpack/webpack-dev-middleware/compare/v5.3.3...v5.3.4)

---
updated-dependencies:
- dependency-name: webpack-dev-middleware
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* Parse Any HTML-esh Style Tags (#2046)

* tried implementing my own regex

* improves tests

* finally works

* removes prints

* fixed test

* adds start and end

* delete unused imports

* refactored to use new tool

* significantly improved algo

* tag content -> tag attr

* fix tests + adds new field

* return full match

* return remove start and end

* update docstrings

* update docstrings

* update docstrings

---------

Co-authored-by: Beibin Li <BeibinLi@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Integrate AgentOptimizer (#1767)

* draft agent optimizer

* refactor

* remove

* change openai config interface

* notebook

* update blog

* add test

* clean up

* redir

* update

* update interface

* change model name

* move to contrib

* Update autogen/agentchat/contrib/agent_optimizer.py

Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>

---------

Co-authored-by: “skzhang1” <“shaokunzhang529@gmail.com”>
Co-authored-by: Beibin Li <BeibinLi@users.noreply.github.com>
Co-authored-by: Jieyu Zhang <jieyuz2@cs.washington.edu>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>

* Introducing IOStream protocol and adding support for websockets (#1551)

* Introducing IOStream

* bug fixing

* polishing

* refactoring

* refactoring

* refactoring

* wip: async tests

* websockets added

* wip

* merge with main

* notebook added

* FastAPI example added

* wip

* merge

* getter/setter to iostream added

* website/blog/2024-03-03-AutoGen-Update/img/dalle_gpt4v.png: convert to Git LFS

* website/blog/2024-03-03-AutoGen-Update/img/gaia.png: convert to Git LFS

* website/blog/2024-03-03-AutoGen-Update/img/teach.png: convert to Git LFS

* add SSL support

* wip

* wip

* exception handling added to on_connect()

* refactoring: default iostream is being set in a context manager

* test fix

* polishing

* polishing

* polishing

* fixed bug with new thread

* polishing

* a bit of refactoring and docs added

* notebook added to docs

* type checking added to CI

* CI fix

* CI fix

* CI fix

* polishing

* obsolete todo comment removed

* fixed precommit error

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* [CAP] [Feature] Get list of actors from directory service. (#2073)

* Search directory for list of actors using regex '.*' gets all actors

* docs changes

* pre-commit fixes

* Use ActorInfo from protobuf

* pre-commit

* Added zmq tests to work on removing sleeps

* minor refactor of zmq tests

* 1) Change DirSvr to user Broker.  2) Add req-router to broker 3) In ActorConnector use handshake and req/resp to remove sleep

* 1) Change DirSvr to user Broker.  2) Add req-router to broker 3) In ActorConnector use handshake and req/resp to remove sleep

* move socket creation to thread with recv

* move socket creation to thread with recv

* Better logging for DirectorySvc

* better logging for directory svc

* Use logging config

* Start removing sleeps

* pre-commit

* Cleanup monitor socket

* Mark cache as a protocol and update type hints to reflect (#2168)

* Mark cache as a protocl and update type hints to reflect

* int

* undo init change

	modified:   autogen/agentchat/chat.py

* fix(): fix word spelling errors (#2171)

* Implement User Defined Functions for Local CLI Executor (#2102)

* Implement user defined functions feature for local cli exec, add docs

* add tests, update docs

* fixes

* fix test

* add pandas test dep

* install test

* provide template as func

* formatting

* undo change

* address comments

* add test deps

* formatting

* test only in 1 env

* formatting

* remove test for local only

---------

Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>

* simplify getting-started; update news (#2175)

* simplify getting-started; update news

* bug fix

* update (#2178)

Co-authored-by: AnonymousRepoSub <“shaokunzhang529@outlook.com” >

* Fix formatting of admonitions in udf docs (#2188)

* Fix iostream on new thread (#2181)

* fixed get_stream in new thread by introducing a global default

* fixed get_stream in new thread by introducing a global default

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Add link for rendering notebooks docs on website (#2191)

* Transform Messages Capability (#1923)

* wip

* Adds docstrings

* fixed spellings

* wip

* fixed errors

* better class names

* adds tests

* added tests to workflow

* improved token counting

* improved notebook

* improved token counting in test

* improved docstrings

* fix inconsistencies

* changed by mistake

* fixed docstring

* fixed details

* improves tests + adds openai contrib test

* fix spelling oai contrib test

* clearer docstrings

* remove repeated docstr

* improved notebook

* adds metadata to notebook

* Improve outline and description (#2125)

* better dir structure

* clip max tokens to allowed tokens

* more accurate comments/docstrs

* add deperecation warning

* fix front matter desc

* add deperecation warning notebook

* undo local notebook settings changes

* format notebook

* format workflow

---------

Co-authored-by: gagb <gagb@users.noreply.github.com>

* Bump express from 4.18.2 to 4.19.2 in /website (#2157)

Bumps [express](https://github.com/expressjs/express) from 4.18.2 to 4.19.2.
- [Release notes](https://github.com/expressjs/express/releases)
- [Changelog](https://github.com/expressjs/express/blob/master/History.md)
- [Commits](https://github.com/expressjs/express/compare/4.18.2...4.19.2)

---
updated-dependencies:
- dependency-name: express
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* add clarity analytics (#2201)

* Docstring formatting fix: Standardize docstrings to adhere to Google style guide, ensuring consistency and clarity. and also fixed the broken link for autogen/agentchat/chat.py

* Docstring fix: Reformattted docstrings to adhere to Google style guide, nsuring consistency and clarity. For agentchat/contrib/retrieve_user_proxy_agent.py file

* Fixed Pre-Commit Error, Trailing spaces on agentchat/chat.py

* Fixed Pre-Commit Error, Trailing spaces on agentchat/chat.py

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
Co-authored-by: Beibin Li <BeibinLi@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: olgavrou <olgavrou@gmail.com>
Co-authored-by: gagb <gagb@users.noreply.github.com>
Co-authored-by: Qingyun Wu <qingyun0327@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Wael Karkoub <wael.karkoub96@gmail.com>
Co-authored-by: Shaokun Zhang <shaokunzhang529@gmail.com>
Co-authored-by: “skzhang1” <“shaokunzhang529@gmail.com”>
Co-authored-by: Jieyu Zhang <jieyuz2@cs.washington.edu>
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
Co-authored-by: Davor Runje <davor@airt.ai>
Co-authored-by: Rajan <rajan.chari@yahoo.com>
Co-authored-by: calm <1191465097@qq.com>
Co-authored-by: AnonymousRepoSub <“shaokunzhang529@outlook.com” >
This commit is contained in:
Harsha S 2024-04-03 08:22:18 +05:30 committed by GitHub
parent 1c22a93535
commit 2053dd9f3d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 118 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

49
autogen/agentchat/chat.py
View File

@ -26,7 +26,9 @@ class ChatResult:
summary: str = None
"""A summary obtained from the chat."""
cost: tuple = None # (dict, dict) - (total_cost, actual_cost_with_cache)
"""The cost of the chat. a tuple of (total_cost, total_actual_cost), where total_cost is a dictionary of cost information, and total_actual_cost is a dictionary of information on the actual incurred cost with cache."""
"""The cost of the chat. a tuple of (total_cost, total_actual_cost), where total_cost is a
dictionary of cost information, and total_actual_cost is a dictionary of information on
the actual incurred cost with cache."""
human_input: List[str] = None
"""A list of human input solicited during the chat."""
@ -141,25 +143,32 @@ def __post_carryover_processing(chat_info: Dict[str, Any]) -> None:
def initiate_chats(chat_queue: List[Dict[str, Any]]) -> List[ChatResult]:
"""Initiate a list of chats.
Args:
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). For example:
- "sender": the sender agent.
- "recipient": the recipient agent.
- "clear_history" (bool): whether to clear the chat history with the agent. Default is True.
- "silent" (bool or None): (Experimental) whether to print the messages in this conversation. Default is False.
- "cache" (AbstractCache or None): the cache client to use for this conversation. Default is None.
- "max_turns" (int or None): maximum number of turns for the chat. If None, the chat will continue until a termination condition is met. Default is None.
- "summary_method" (str or callable): a string or callable specifying the method to get a summary from the chat. Default is DEFAULT_summary_method, i.e., "last_msg".
- "summary_args" (dict): a dictionary of arguments to be passed to the summary_method. Default is {}.
- "message" (str, callable or None): if None, input() will be called to get the initial message.
- **context: additional context information to be passed to the chat.
- "carryover": It can be used to specify the carryover information to be passed to this chat.
If provided, we will combine this carryover with the "message" content when generating the initial chat
message in `generate_init_message`.
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).
For example:
- `"sender"` - the sender agent.
- `"recipient"` - the recipient agent.
- `"clear_history" (bool) - whether to clear the chat history with the agent.
Default is True.
- `"silent"` (bool or None) - (Experimental) whether to print the messages in this
conversation. Default is False.
- `"cache"` (Cache or None) - the cache client to use for this conversation.
Default is None.
- `"max_turns"` (int or None) - maximum number of turns for the chat. If None, the chat
will continue until a termination condition is met. Default is None.
- `"summary_method"` (str or callable) - a string or callable specifying the method to get
a summary from the chat. Default is DEFAULT_summary_method, i.e., "last_msg".
- `"summary_args"` (dict) - a dictionary of arguments to be passed to the summary_method.
Default is {}.
- `"message"` (str, callable or None) - if None, input() will be called to get the
initial message.
- `**context` - additional context information to be passed to the chat.
- `"carryover"` - It can be used to specify the carryover information to be passed
to this chat. If provided, we will combine this carryover with the "message" content when
generating the initial chat message in `generate_init_message`.
Returns:
(list): a list of ChatResult objects corresponding to the finished chats in the chat_queue.
"""
@ -228,11 +237,11 @@ async def a_initiate_chats(chat_queue: List[Dict[str, Any]]) -> Dict[int, ChatRe
"""(async) Initiate a list of chats.
args:
Please refer to `initiate_chats`.
- Please refer to `initiate_chats`.
returns:
(Dict): a dict of ChatId: ChatResult corresponding to the finished chats in the chat_queue.
- (Dict): a dict of ChatId: ChatResult corresponding to the finished chats in the chat_queue.
"""
consolidate_chat_info(chat_queue)
_validate_recipients(chat_queue)

135
autogen/agentchat/contrib/retrieve_user_proxy_agent.py
View File

@ -62,6 +62,10 @@ Context is: {input_context}
class RetrieveUserProxyAgent(UserProxyAgent):
"""(In preview) The Retrieval-Augmented User Proxy retrieves document chunks based on the embedding
similarity, and sends them along with the question to the Retrieval-Augmented Assistant
"""
def __init__(
self,
name="RetrieveChatAgent", # default set to RetrieveChatAgent
@ -73,67 +77,106 @@ class RetrieveUserProxyAgent(UserProxyAgent):
r"""
Args:
name (str): name of the agent.
human_input_mode (str): whether to ask for human inputs every time a message is received.
Possible values are "ALWAYS", "TERMINATE", "NEVER".
1. When "ALWAYS", the agent prompts for human input every time a message is received.
Under this mode, the conversation stops when the human input is "exit",
or when is_termination_msg is True and there is no human input.
2. When "TERMINATE", the agent only prompts for human input only when a termination message is received or
the number of auto reply reaches the max_consecutive_auto_reply.
3. When "NEVER", the agent will never prompt for human input. Under this mode, the conversation stops
when the number of auto reply reaches the max_consecutive_auto_reply or when is_termination_msg is True.
2. When "TERMINATE", the agent only prompts for human input only when a termination
message is received or the number of auto reply reaches
the max_consecutive_auto_reply.
3. When "NEVER", the agent will never prompt for human input. Under this mode, the
conversation stops when the number of auto reply reaches the
max_consecutive_auto_reply or when is_termination_msg is True.
is_termination_msg (function): a function that takes a message in the form of a dictionary
and returns a boolean value indicating if this received message is a termination message.
The dict can contain the following keys: "content", "role", "name", "function_call".
retrieve_config (dict or None): config for the retrieve agent.
To use default config, set to None. Otherwise, set to a dictionary with the following keys:
- task (Optional, str): the task of the retrieve chat. Possible values are "code", "qa" and "default". System
prompt will be different for different tasks. The default value is `default`, which supports both code and qa.
- client (Optional, chromadb.Client): the chromadb client. If key not provided, a default client `chromadb.Client()`
will be used. If you want to use other vector db, extend this class and override the `retrieve_docs` function.
- docs_path (Optional, Union[str, List[str]]): the path to the docs directory. It can also be the path to a single file,
the url to a single file or a list of directories, files and urls. Default is None, which works only if the collection is already created.
- extra_docs (Optional, bool): when true, allows adding documents with unique IDs without overwriting existing ones; when false, it replaces existing documents using default IDs, risking collection overwrite.,
when set to true it enables the system to assign unique IDs starting from "length+i" for new document chunks, preventing the replacement of existing documents and facilitating the addition of more content to the collection..
By default, "extra_docs" is set to false, starting document IDs from zero. This poses a risk as new documents might overwrite existing ones, potentially causing unintended loss or alteration of data in the collection.
- collection_name (Optional, str): the name of the collection.
To use default config, set to None. Otherwise, set to a dictionary with the
following keys:
- `task` (Optional, str) - the task of the retrieve chat. Possible values are
"code", "qa" and "default". System prompt will be different for different tasks.
The default value is `default`, which supports both code and qa.
- `client` (Optional, chromadb.Client) - the chromadb client. If key not provided, a
default client `chromadb.Client()` will be used. If you want to use other
vector db, extend this class and override the `retrieve_docs` function.
- `docs_path` (Optional, Union[str, List[str]]) - the path to the docs directory. It
can also be the path to a single file, the url to a single file or a list
of directories, files and urls. Default is None, which works only if the
collection is already created.
- `extra_docs` (Optional, bool) - when true, allows adding documents with unique IDs
without overwriting existing ones; when false, it replaces existing documents
using default IDs, risking collection overwrite., when set to true it enables
the system to assign unique IDs starting from "length+i" for new document
chunks, preventing the replacement of existing documents and facilitating the
addition of more content to the collection..
By default, "extra_docs" is set to false, starting document IDs from zero.
This poses a risk as new documents might overwrite existing ones, potentially
causing unintended loss or alteration of data in the collection.
- `collection_name` (Optional, str) - the name of the collection.
If key not provided, a default name `autogen-docs` will be used.
- model (Optional, str): the model to use for the retrieve chat.
- `model` (Optional, str) - the model to use for the retrieve chat.
If key not provided, a default model `gpt-4` will be used.
- chunk_token_size (Optional, int): the chunk token size for the retrieve chat.
- `chunk_token_size` (Optional, int) - the chunk token size for the retrieve chat.
If key not provided, a default size `max_tokens * 0.4` will be used.
- context_max_tokens (Optional, int): the context max token size for the retrieve chat.
- `context_max_tokens` (Optional, int) - the context max token size for the
retrieve chat.
If key not provided, a default size `max_tokens * 0.8` will be used.
- chunk_mode (Optional, str): the chunk mode for the retrieve chat. Possible values are
"multi_lines" and "one_line". If key not provided, a default mode `multi_lines` will be used.
- must_break_at_empty_line (Optional, bool): chunk will only break at empty line if True. Default is True.
- `chunk_mode` (Optional, str) - the chunk mode for the retrieve chat. Possible values
are "multi_lines" and "one_line". If key not provided, a default mode
`multi_lines` will be used.
- `must_break_at_empty_line` (Optional, bool) - chunk will only break at empty line
if True. Default is True.
If chunk_mode is "one_line", this parameter will be ignored.
- embedding_model (Optional, str): the embedding model to use for the retrieve chat.
If key not provided, a default model `all-MiniLM-L6-v2` will be used. All available models
can be found at `https://www.sbert.net/docs/pretrained_models.html`. The default model is a
fast model. If you want to use a high performance model, `all-mpnet-base-v2` is recommended.
- embedding_function (Optional, Callable): the embedding function for creating the vector db. Default is None,
SentenceTransformer with the given `embedding_model` will be used. If you want to use OpenAI, Cohere, HuggingFace or
other embedding functions, you can pass it here, follow the examples in `https://docs.trychroma.com/embeddings`.
- customized_prompt (Optional, str): the customized prompt for the retrieve chat. Default is None.
- customized_answer_prefix (Optional, str): the customized answer prefix for the retrieve chat. Default is "".
If not "" and the customized_answer_prefix is not in the answer, `Update Context` will be triggered.
- update_context (Optional, bool): if False, will not apply `Update Context` for interactive retrieval. Default is True.
- get_or_create (Optional, bool): if True, will create/return a collection for the retrieve chat. This is the same as that used in chromadb.
Default is False. Will raise ValueError if the collection already exists and get_or_create is False. Will be set to True if docs_path is None.
- custom_token_count_function (Optional, Callable): a custom function to count the number of tokens in a string.
The function should take (text:str, model:str) as input and return the token_count(int). the retrieve_config["model"] will be passed in the function.
Default is autogen.token_count_utils.count_token that uses tiktoken, which may not be accurate for non-OpenAI models.
- custom_text_split_function (Optional, Callable): a custom function to split a string into a list of strings.
Default is None, will use the default function in `autogen.retrieve_utils.split_text_to_chunks`.
- custom_text_types (Optional, List[str]): a list of file types to be processed. Default is `autogen.retrieve_utils.TEXT_FORMATS`.
This only applies to files under the directories in `docs_path`. Explicitly included files and urls will be chunked regardless of their types.
- recursive (Optional, bool): whether to search documents recursively in the docs_path. Default is True.
- `embedding_model` (Optional, str) - the embedding model to use for the retrieve chat.
If key not provided, a default model `all-MiniLM-L6-v2` will be used. All available
models can be found at `https://www.sbert.net/docs/pretrained_models.html`.
The default model is a fast model. If you want to use a high performance model,
`all-mpnet-base-v2` is recommended.
- `embedding_function` (Optional, Callable) - the embedding function for creating the
vector db. Default is None, SentenceTransformer with the given `embedding_model`
will be used. If you want to use OpenAI, Cohere, HuggingFace or other embedding
functions, you can pass it here,
follow the examples in `https://docs.trychroma.com/embeddings`.
- `customized_prompt` (Optional, str) - the customized prompt for the retrieve chat.
Default is None.
- `customized_answer_prefix` (Optional, str) - the customized answer prefix for the
retrieve chat. Default is "".
If not "" and the customized_answer_prefix is not in the answer,
`Update Context` will be triggered.
- `update_context` (Optional, bool) - if False, will not apply `Update Context` for
interactive retrieval. Default is True.
- `get_or_create` (Optional, bool) - if True, will create/return a collection for the
retrieve chat. This is the same as that used in chromadb.
Default is False. Will raise ValueError if the collection already exists and
get_or_create is False. Will be set to True if docs_path is None.
- `custom_token_count_function` (Optional, Callable) - a custom function to count the
number of tokens in a string.
The function should take (text:str, model:str) as input and return the
token_count(int). the retrieve_config["model"] will be passed in the function.
Default is autogen.token_count_utils.count_token that uses tiktoken, which may
not be accurate for non-OpenAI models.
- `custom_text_split_function` (Optional, Callable) - a custom function to split a
string into a list of strings.
Default is None, will use the default function in
`autogen.retrieve_utils.split_text_to_chunks`.
- `custom_text_types` (Optional, List[str]) - a list of file types to be processed.
Default is `autogen.retrieve_utils.TEXT_FORMATS`.
This only applies to files under the directories in `docs_path`. Explicitly
included files and urls will be chunked regardless of their types.
- `recursive` (Optional, bool) - whether to search documents recursively in the
docs_path. Default is True.
`**kwargs` (dict): other kwargs in [UserProxyAgent](../user_proxy_agent#__init__).
Example:
Example of overriding retrieve_docs - If you have set up a customized vector db, and it's not compatible with chromadb, you can easily plug in it with below code.
Example of overriding retrieve_docs - If you have set up a customized vector db, and it's
not compatible with chromadb, you can easily plug in it with below code.
```python
class MyRetrieveUserProxyAgent(RetrieveUserProxyAgent):
def query_vector_db(
@ -416,9 +459,9 @@ class RetrieveUserProxyAgent(UserProxyAgent):
sender (Agent): the sender agent. It should be the instance of RetrieveUserProxyAgent.
recipient (Agent): the recipient agent. Usually it's the assistant agent.
context (dict): the context for the message generation. It should contain the following keys:
- problem (str): the problem to be solved.
- n_results (int): the number of results to be retrieved. Default is 20.
- search_string (str): only docs that contain an exact match of this string will be retrieved. Default is "".
- `problem` (str) - the problem to be solved.
- `n_results` (int) - the number of results to be retrieved. Default is 20.
- `search_string` (str) - only docs that contain an exact match of this string will be retrieved. Default is "".
Returns:
str: the generated message ready to be sent to the recipient agent.
"""