Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+output.db filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+from ques_1 import driver1
+# from ques_2 import driver2
+
+q1 = gr.Interface(
+    fn=driver1,
+    inputs=gr.Textbox(
+        label="Enter your industry to know more about the customers that use salesforce: ",
+        info="Food, Health care, Sports, etc...",
+        lines=1,
+    ),
+    outputs="text",
+)
+
+q2 = gr.Interface(
+    fn=driver1,
+    inputs=gr.Textbox(
+        label="Enter your customer to know more about how they leverage salesforce",
+        info="Williams-Sonoma Inc., ReserveBar, Christy Sports, etc...",
+        lines=1,
+    ),
+    outputs="text",
+)
+
+app = gr.TabbedInterface([q1, q2], ["Industry based Customers", "Customer stories leveraging Salesforce"])
+
+if __name__ == "__main__":
+    app.launch()

env.py

@@ -0,0 +1,9 @@
+OPENAI_API_KEY = "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"
+# snowflake_account = "JGIYHFR.BW66671"
+# snowflake_account = "jgiyhfr-bw66671"
+# username = "srini047"
+# password = "Football1234%"
+# database = "salesforce-scraped"
+# schema = "public"
+# warehouse = "compute_wh"
+# role = "accountadmin"

output.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701848626db7db581c8cee7699f7e813143fe100ddbdd49dd10b666008bdd14a
+size 1265664

ques_1.py

@@ -0,0 +1,27 @@
+from langchain import OpenAI, SQLDatabase
+from langchain.agents.agent_toolkits import SQLDatabaseToolkit
+from langchain.agents import create_sql_agent
+from langchain.agents import AgentExecutor
+from langchain.agents.agent_types import AgentType
+from env import OPENAI_API_KEY
+
+dburi = "sqlite:///output.db"
+db = SQLDatabase.from_uri(dburi)
+llm = OpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)
+
+toolkit = SQLDatabaseToolkit(db=db, llm=llm)
+agent_executor = create_sql_agent(
+    llm=llm,
+    toolkit=toolkit,
+    verbose=True,
+    agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+)
+
+
+def driver1(industry_type):
+    response = agent_executor.run(
+        "What are the customers in"
+        + industry_type
+        + " industry that chose salesforce? Give the answer in form of bullet points ->"
+    )
+    return response

ques_2.py

@@ -0,0 +1,51 @@
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Chroma
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+from langchain.schema.runnable import RunnablePassthrough
+from langchain.prompts import PromptTemplate
+from langchain import hub
+from env import OPENAI_API_KEY
+
+def main():
+    loader = CSVLoader(file_path="output.csv")
+    data = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
+    splits = text_splitter.split_documents(data)
+    vectorstore = Chroma.from_documents(
+        documents=splits,
+        embedding=OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY),
+    )
+    retriever = vectorstore.as_retriever()
+    rag_prompt = hub.pull("rlm/rag-prompt")
+    llm = ChatOpenAI(
+        model_name="gpt-3.5-turbo",
+        temperature=0,
+        openai_api_key=OPENAI_API_KEY,
+    )
+    template = """Use the following pieces of context to answer the question at the end. 
+    If you don't know the answer, just say that you don't know, don't try to make up an answer. 
+    Use three sentences maximum and keep the answer as concise as possible.
+    {context}
+    Question: {question}
+    Helpful Answer:"""
+    rag_prompt_custom = PromptTemplate.from_template(template)
+
+    rag_chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | rag_prompt_custom
+        | llm
+    )
+    return rag_chain
+
+
+def driver2(customer_name):
+    rag_chain = main()
+    response = rag_chain.invoke(
+        "Can you tell me more about customer"
+        + customer_name
+        + " and how they benefited from salesforce?"
+    )
+    print(response)
+    return response.content

requirements.txt

@@ -0,0 +1,85 @@
+aiofiles==23.2.1
+aiohttp==3.9.1
+aiosignal==1.3.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==3.7.1
+async-timeout==4.0.3
+attrs==23.1.0
+certifi==2023.11.17
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+dataclasses-json==0.6.3
+distro==1.8.0
+exceptiongroup==1.2.0
+fastapi==0.104.1
+ffmpy==0.3.1
+filelock==3.13.1
+fonttools==4.45.1
+frozenlist==1.4.0
+fsspec==2023.10.0
+gradio==4.7.1
+gradio_client==0.7.0
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.25.2
+huggingface-hub==0.19.4
+idna==3.6
+importlib-resources==6.1.1
+Jinja2==3.1.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.20.0
+jsonschema-specifications==2023.11.2
+kiwisolver==1.4.5
+langchain==0.0.344
+langchain-core==0.0.8
+langsmith==0.0.68
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+matplotlib==3.8.2
+mdurl==0.1.2
+multidict==6.0.4
+mypy-extensions==1.0.0
+numpy==1.26.2
+openai==1.3.7
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.3
+Pillow==10.1.0
+pydantic==2.5.2
+pydantic_core==2.14.5
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.31.1
+requests==2.31.0
+rich==13.7.0
+rpds-py==0.13.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.0
+SQLAlchemy==2.0.23
+starlette==0.27.0
+tenacity==8.2.3
+tomlkit==0.12.0
+toolz==0.12.0
+tqdm==4.66.1
+typer==0.9.0
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+urllib3==2.1.0
+uvicorn==0.24.0.post1
+websockets==11.0.3
+yarl==1.9.3
+zipp==3.17.0