Add Enum for agent types

[Shrined]

This pull request adds an enum class for the various types of agents used in the project, located in the agent_types.py file. Currently, the project is using hardcoded strings for the initialization of these agents, which can lead to errors and make the code harder to maintain. With the introduction of the new enums, the code will be more readable and less error-prone.

The new enum members include:

• ZERO_SHOT_REACT_DESCRIPTION
• REACT_DOCSTORE
• SELF_ASK_WITH_SEARCH
• CONVERSATIONAL_REACT_DESCRIPTION
• CHAT_ZERO_SHOT_REACT_DESCRIPTION
• CHAT_CONVERSATIONAL_REACT_DESCRIPTION

In this PR, I have also replaced the hardcoded strings with the appropriate enum members throughout the codebase, ensuring a smooth transition to the new approach.

[sergerdn]

I'm sorry to be the bearer of bad news, but I need to inform you that...

 grep -r "zero-shot-react-description"  docs/

docs/ecosystem/aim_tracking.ipynb:    "    agent=\"zero-shot-react-description\",\n",
docs/ecosystem/clearml_tracking.ipynb:    "    agent=\"zero-shot-react-description\",\n",
docs/ecosystem/wandb_tracking.ipynb:    "    agent=\"zero-shot-react-description\",\n",
docs/getting_started/getting_started.md:agent = initialize_agent(tools, llm, agent="zero-shot-react-description", verbose=True)
docs/getting_started/getting_started.md:Agents can also be used with chat models, you can initialize one using `"chat-zero-shot-react-description"` as the agent type.
docs/getting_started/getting_started.md:agent = initialize_agent(tools, chat, agent="chat-zero-shot-react-description", verbose=True)
docs/modules/agents/agents/agent_types.md:## `zero-shot-react-description`
docs/modules/agents/agents/examples/mrkl.ipynb:    "mrkl = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/agents/examples/mrkl_chat.ipynb:    "mrkl = initialize_agent(tools, llm, agent=\"chat-zero-shot-react-description\", verbose=True)"
docs/modules/agents/agent_executors/examples/agent_vectorstore.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/agent_executors/examples/agent_vectorstore.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/agent_executors/examples/agent_vectorstore.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/agent_executors/examples/async_agent.ipynb:    "            tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
docs/modules/agents/agent_executors/examples/async_agent.ipynb:    "            initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
docs/modules/agents/agent_executors/examples/async_agent.ipynb:    "async_agent = initialize_agent(async_tools, llm, agent=\"zero-shot-react-description\", verbose=True, callback_manager=manager)\n",
docs/modules/agents/agent_executors/examples/intermediate_steps.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True, return_intermediate_steps=True)"
docs/modules/agents/agent_executors/examples/max_iterations.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/agent_executors/examples/max_iterations.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True, max_iterations=2)"
docs/modules/agents/agent_executors/examples/max_iterations.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True, max_iterations=2, early_stopping_method=\"generate\")"
docs/modules/agents/getting_started.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/how_to_guides.rst:- **Agent used**: `zero-shot-react-description`
docs/modules/agents/tools/custom_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/custom_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/custom_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/custom_tools.ipynb:    "agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/custom_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/examples/chatgpt_plugins.ipynb:    "agent_chain = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)\n",
docs/modules/agents/tools/examples/human_tools.ipynb:    "    agent=\"zero-shot-react-description\",\n",
docs/modules/agents/tools/examples/search_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/examples/search_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/examples/search_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/examples/search_tools.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/examples/zapier.ipynb:    "agent = initialize_agent(toolkit.get_tools(), llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/agents/tools/multi_input_tool.ipynb:    "mrkl = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/models/llms/examples/fake_llm.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/modules/models/llms/examples/token_usage_tracking.ipynb:    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
docs/tracing/agent_with_tracing.ipynb:    "    tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
docs/tracing/agent_with_tracing.ipynb:    "    tools, ChatOpenAI(temperature=0), agent=\"chat-zero-shot-react-description\", verbose=True\n",
docs/use_cases/evaluation/agent_benchmarking.ipynb:    "agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\")\n"
docs/use_cases/evaluation/agent_vectordb_sota_pg.ipynb:    "agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\", max_iterations=3)"

[Shrined]

Addressed the issue where hardcoded strings instead of the AgentType enums were still being used in some of the examples within the documentation.

[hwchase17]

this is awesome.

thinking about backwards compatibility - this will still work for people on the old version, right? because the string is still the same under the hood?

[Shrined]

this is awesome.

thinking about backwards compatibility - this will still work for people on the old version, right? because the string is still the same under the hood?

Yes, exactly. Due to the AgentType class inheriting from str, the underlying string representation is maintained, ensuring backwards compatibility for users on older versions.

[hwchase17]

thanks!