Validated Bigframes.pands package to query BQ

.gitignore

@@ -2,3 +2,10 @@
 .DS_Store
 webapp/.env
 *.pyc
+
+# Segmentation use-cases
+# langserve/packages/bq-agent/bq_agent/dev
+
+# Original agent.py
+langserve/packages/bq-agent/bq_agent/agent_original.py
+

langserve/packages/bq-agent/README.md

@@ -0,0 +1,71 @@
+
+# csv-agent
+
+This template uses a [pandas agent](https://python.langchain.com/docs/integrations/toolkits/pandas) with tools [BigQuery DataFrames](https://cloud.google.com/python/docs/reference/bigframes/latest) to read a BigQuery table for interaction (question-answering) with tabular data.
+
+## Environment Setup
+
+Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
+
+
+## Usage
+
+To use this package, you should first have the LangChain CLI installed:
+
+```shell
+pip install -U langchain-cli
+```
+
+To create a new LangChain project and install this as the only package, you can do:
+
+```shell
+langchain app new my-app --package bq-agent
+```
+
+If you want to add this to an existing project, you can just run:
+
+```shell
+langchain app add bq-agent
+```
+
+And add the following code to your `server.py` file:
+```python
+
+from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
+
+
+add_routes(app, csv_agent_chain, path="/bq-agent")
+```
+
+(Optional) Let's now configure LangSmith. 
+LangSmith will help us trace, monitor and debug LangChain applications. 
+LangSmith is currently in private beta, you can sign up [here](https://smith.langchain.com/). 
+If you don't have access, you can skip this section
+
+
+```shell
+export LANGCHAIN_TRACING_V2=true
+export LANGCHAIN_API_KEY=<your-api-key>
+export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"
+```
+
+If you are inside this directory, then you can spin up a LangServe instance directly by:
+
+```shell
+langchain serve
+```
+
+This will start the FastAPI app with a server is running locally at 
+[http://localhost:8000](http://localhost:8000)
+
+We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
+
+We can access the playground at [http://127.0.0.1:8000/bq-agent/playground](http://127.0.0.1:8000/bq-agent/playground)  
+
+We can access the template from code with:
+
+```python
+from langserve.client import RemoteRunnable
+
+runnable = RemoteRunnable("http://localhost:8000/csv-agent")
+```

langserve/packages/bq-agent/bq_agent/__init__.py

@@ -0,0 +1,3 @@
+from bq_agent.agent import agent_executor
+
+__all__ = ["agent_executor"]

langserve/packages/bq-agent/bq_agent/agent.py

@@ -0,0 +1,31 @@
+from pathlib import Path
+
+import pandas as pd
+from langchain.agents import AgentExecutor, OpenAIFunctionsAgent
+# from langchain.chat_models import ChatOpenAI
+# from langchain.embeddings import OpenAIEmbeddings
+# from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+# from langchain.pydantic_v1 import BaseModel, Field
+# from langchain.tools.retriever import create_retriever_tool
+# from langchain.vectorstores import FAISS
+# from langchain_experimental.tools import PythonAstREPLTool
+import bigframes.pandas as bpd
+from langchain.agents.agent_types import AgentType
+from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
+from langchain_openai import ChatOpenAI
+from langchain_openai import OpenAI
+
+
+
+# Load data
+df = bpd.read_gbq("SELECT name, job, created, transactions, revenue, permission, crm_id, FROM `annular-form-389809.merged_data.crm_ga4`LIMIT 45").to_pandas()
+
+# Defining agent
+agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)
+
+# Default prompt
+agent.run("How many rows are there in this dataframe?")
+
+# Defining agent executor
+agent_executor = AgentExecutor(
+    agent=agent)