bump to 0058 (#556)

docs/modules/memory/how_to_guides.rst

@@ -15,6 +15,8 @@ The examples here all highlight how to use memory in different ways.
 
 `Adding Memory to Agents <./examples/agent_with_memory.html>`_: How to add a memory component to any agent.
 
+`Conversation Agent <./examples/conversational_agent.html>`_: Example of a conversation agent, which combines memory with agents and a conversation focused prompt.
+
 
 .. toctree::
    :maxdepth: 1

docs/use_cases/chatbots.md

@@ -7,6 +7,7 @@ Most chat based applications rely on remembering what happened in previous inter
 The following resources exist:
 - [ChatGPT Clone](../modules/memory/examples/chatgpt_clone.ipynb): A notebook walking through how to recreate a ChatGPT-like experience with LangChain.
 - [Conversation Memory](../modules/memory/getting_started.ipynb): A notebook walking through how to use different types of conversational memory.
+- [Conversation Agent](../modules/memory/examples/conversational_agent.ipynb): A notebook walking through how to create an agent optimized for conversation.
 
 
 Additional related resources include:

langchain/llms/openai.py

@@ -171,8 +171,8 @@ class BaseOpenAI(BaseLLM, BaseModel):
                     Generation(
                         text=choice["text"],
                         generation_info=dict(
-                            finish_reason=choice["finish_reason"],
+                            finish_reason=choice.get("finish_reason"),
-                            logprobs=choice["logprobs"],
+                            logprobs=choice.get("logprobs"),
                         ),
                     )
                     for choice in sub_choices

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain"
-version = "0.0.57"
+version = "0.0.58"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"