0.1.247

Agent: during init, set config.parsing.token_encoding_model to the LLM,
so we use the tokenizer specific to the LLM, which helps with accurate token-cost computation.
(only affects OpenAI LLMs currently).

0.1.246

• Fix ChainlitTaskCallbacks - use classmethod not staticmethod, so any derived versions propagate to subtasks
• Handle deviant OpenAI LLM function-call generation (esp w gpt-4o), e.g. functions with name "functions", or "functions xyz"

0.1.245

• Improve LanceDocChatAgent and Query Planner to handle deviations.
• Handle function-call odditities in OpenAI LLM -- they can generate an unnecessary "name" field, which we override with the "request" field from the arguments.

0.1.244

• Tweaks to LanceDocChatAgent and related Agents (QueryPlanner, Critic, etc) to accomodate deviations
• In multi-agent chats, so total cost across all agents, in addition to cumul cost of current agent

0.1.243

Update toml to latest DuckDuckGo (6.0.0) so we no longer get the rate limit error

0.1.242

Support OpenAI GPT-4o -- this is now the default LLM when no model is specified.

To explicitly specify the LLM, you can do, for example:

import langroid.language_models as lm
llm = lm.OpenAIGPT( lm.OpenAIGPTConfig(chat_model = lm.OpenAIChatModel.GPT4o))

And recall you can run most of the example scripts with a model specified via -m gpt-4o,
and pytests using --m gpt-4o

0.1.241

Gemini support via litellm. See docs https://langroid.github.io/langroid/tutorials/non-openai-llms/

Essentially, you need to:

• install langroid with the litellm extra, e.g. pip install "langroid[litellm]"
• set up your GEMINI_API_KEY in the .env file or shell env
• specify chat_model="litellm/gemini/gemini-1.5-pro-latest"

0.1.240

QdrantDB, QdrantDBConfig: support for sparse embeddings

0.1.239

Change python range to >= 3.10 < 3.12 to avoid colab errors (used to be >= 3.11)

0.1.238

Minor type sig change