Merge pull request #83 from filip-michalsky/langsmith

Langsmith implementation

.gitignore

@@ -197,3 +197,4 @@ internal/*
 *_phoneme.npy
 wandb
 depot/*
+litellm_uuid.txt

README.md

@@ -59,6 +59,9 @@ The AI Sales Agent understands the conversation stage (you can define your own s
 ### Human in the loop
 - For use cases where AI sales agent needs human supervision.
 
+### Langsmith tracing
+- debug, test, evaluate, and monitor chains and intelligent agents built on any LLM framework
+
 ### Enterprise-Grade Security
 
 - Upcoming integration with [PromptArmor](https://promptarmor.com/) to protect your AI Sales Agents against security vulnerabilities (see our roadmap).
@@ -247,6 +250,24 @@ Please refer to [README-api.md](https://github.com/filip-michalsky/SalesGPT/blob
 
 We leverage the [`langchain`](https://github.com/hwchase17/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture.
 
+## LangSmith tracing
+
+LangSmith is a platform for building production-grade LLM applications.
+
+It lets you debug, test, evaluate, and monitor chains and intelligent agents built on any LLM framework and seamlessly integrates with LangChain, the go-to open source framework for building with LLMs.
+
+LangSmith is developed by LangChain, the company behind the open source LangChain framework.
+
+To switch on the LangSmith tracing you have to do the following steps:
+
+1. [Create a LangSmith account](https://smith.langchain.com/)
+2. [Create an API key in settings](https://smith.langchain.com/settings)
+3. Add you API key and Project name from LangSmith account to .env file or run.py module
+4. Switch on the "LANGCHAIN_TRACING_V2" setting in run.py to "true"
+5. That's it. You'll get better understanding of your agents and chaing performance in LangChain admin panel. 
+
+For futher reading take a look at the [docs](https://docs.smith.langchain.com/)
+
 # Roadmap
 
 1) Documenting the Repo better

run.py

@@ -1,5 +1,6 @@
 import argparse
 import json
+import os
 
 from dotenv import load_dotenv
 from langchain.chat_models import ChatLiteLLM
@@ -8,6 +9,12 @@
 
 load_dotenv()  # loads .env file
 
+# LangSmith settings section, set TRACING_V2 to "true" to enable it
+# or leave it as it is, if you don't need tracing (more info in README)
+os.environ["LANGCHAIN_TRACING_V2"] = "false"
+os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com"
+os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_SMITH_API_KEY")
+os.environ["LANGCHAIN_PROJECT"] = ""  # insert you project name here
 
 if __name__ == "__main__":
     # Initialize argparse