primer commit

app.py

@@ -0,0 +1,62 @@
+from typing import Set
+
+from backend.core import run_llm
+import streamlit as st
+from streamlit_chat import message
+from langchain.output_parsers import ResponseSchema
+#from langchain.document_loaders import PyPDFLoader
+
+def create_sources_string(source_urls: Set[str]) -> str:
+    if not source_urls:
+        return ""
+    sources_list = list(source_urls)
+    sources_list.sort()
+    sources_string = "sources:\n"
+    for i, source in enumerate(sources_list):
+        sources_string += f"{i+1}. {source}\n"
+    return sources_string
+
+
+st.header("Chatbot Documentos Nico")
+if (
+    "chat_answers_history" not in st.session_state
+    and "user_prompt_history" not in st.session_state
+    and "chat_history" not in st.session_state
+):
+    st.session_state["chat_answers_history"] = []
+    st.session_state["user_prompt_history"] = []
+    st.session_state["chat_history"] = []
+
+
+prompt = st.text_input("Chatbot", placeholder="Quieres saber algo? pregunta aquí ...") or st.button(
+    "Submit"
+)
+
+if prompt:
+    with st.spinner("Generating response..."):
+        generated_response = run_llm(
+            query=prompt, chat_history=st.session_state["chat_history"]
+        )
+
+        sources = set(
+            [(doc.metadata["page"], doc.metadata["source"]) for doc in generated_response["source_documents"]]
+        )
+        #sources = set([1,2])
+        formatted_response = (
+            f"{generated_response['answer']} \n\n {create_sources_string(sources)}"
+        )
+
+        st.session_state.chat_history.append((prompt, generated_response["answer"]))
+        st.session_state.user_prompt_history.append(prompt)
+        st.session_state.chat_answers_history.append(formatted_response)
+
+if st.session_state["chat_answers_history"]:
+    for generated_response, user_query in zip(
+        st.session_state["chat_answers_history"],
+        st.session_state["user_prompt_history"],
+    ):
+        message(
+            user_query,
+            is_user=True,
+        )
+        message(generated_response)

backend/core.py

@@ -0,0 +1,39 @@
+import os
+from typing import Any, Dict, List
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chains import RetrievalQA
+from langchain.vectorstores import Chroma
+from langchain.output_parsers import ResponseSchema
+from langchain.output_parsers import StructuredOutputParser
+from langchain.document_loaders import PyPDFLoader
+from langchain.prompts import ChatPromptTemplate
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+persist_directory = 'chroma/'
+
+def run_llm(query: str, chat_history: List[Dict[str, Any]] = []):
+    
+    embeddings = OpenAIEmbeddings(openai_api_key=os.environ["OPENAI_API_KEY"])
+    
+    new_vectorstore = Chroma(persist_directory=persist_directory, embedding_function=embeddings)
+       
+    chat = ChatOpenAI(
+        model="gpt-3.5-turbo-16k",
+        verbose=True,
+        temperature=0,
+    )
+
+    qa = ConversationalRetrievalChain.from_llm(
+        llm=chat, retriever=new_vectorstore.as_retriever(search_type = "mmr", search_kwargs={"k": 6, "fetch_k":20}), return_source_documents=True
+     )
+
+    return qa({"question": query, "chat_history": chat_history})
+
+if __name__ == "__main__":
+    print(run_llm(query="What is Venu 2?"))

requirements.txt

@@ -0,0 +1,125 @@
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.0.1
+anyio==3.7.1
+arabic-reshaper==3.0.0
+asgiref==3.7.2
+asn1crypto==1.5.1
+async-timeout==4.0.3
+attrs==23.1.0
+backoff==2.2.1
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+cffi==1.15.1
+charset-normalizer==3.2.0
+chroma-hnswlib==0.7.2
+chromadb==0.4.5
+click==8.1.6
+coloredlogs==15.0.1
+cryptography==41.0.3
+cssselect2==0.7.0
+dataclasses-json==0.5.14
+decorator==5.1.1
+Django==4.2.4
+fastapi==0.99.1
+flatbuffers==23.5.26
+frozenlist==1.4.0
+gitdb==4.0.10
+GitPython==3.1.32
+greenlet==2.0.2
+h11==0.14.0
+html5lib==1.1
+httptools==0.6.0
+humanfriendly==10.0
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.0.1
+Jinja2==3.1.2
+jsonschema==4.19.0
+jsonschema-specifications==2023.7.1
+langchain==0.0.273
+langsmith==0.0.26
+lxml==4.9.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+numexpr==2.8.5
+numpy==1.25.2
+onnxruntime==1.15.1
+openai==0.27.9
+openapi-schema-pydantic==1.2.4
+oscrypto==1.3.0
+overrides==7.4.0
+packaging==23.1
+pandas==2.0.3
+pdf2image==1.16.3
+Pillow==9.5.0
+posthog==3.0.1
+protobuf==4.24.0
+pulsar-client==3.2.0
+pyarrow==12.0.1
+pycparser==2.21
+pydantic==1.10.12
+pydeck==0.8.0
+Pygments==2.16.1
+pyHanko==0.20.0
+pyhanko-certvalidator==0.23.0
+Pympler==1.0.1
+pypdf==3.15.0
+PyPDF2==3.0.1
+PyPika==0.48.9
+pypng==0.20220715.0
+pytesseract==0.3.10
+python-bidi==0.4.2
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0.1
+qrcode==7.4.2
+referencing==0.30.2
+regex==2023.8.8
+reportlab==3.6.13
+requests==2.31.0
+rich==13.5.2
+rpds-py==0.9.2
+six==1.16.0
+smmap==5.0.0
+sniffio==1.3.0
+SQLAlchemy==2.0.19
+sqlparse==0.4.4
+starlette==0.27.0
+streamlit==1.25.0
+streamlit-chat==0.1.1
+svglib==1.5.1
+sympy==1.12
+tenacity==8.2.2
+tiktoken==0.4.0
+tinycss2==1.2.1
+tokenizers==0.13.3
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.2
+tqdm==4.66.1
+typing-inspect==0.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+uritools==4.0.1
+urllib3==2.0.4
+uvicorn==0.23.2
+uvloop==0.17.0
+validators==0.20.0
+watchdog==3.0.0
+watchfiles==0.19.0
+webencodings==0.5.1
+websockets==11.0.3
+xhtml2pdf==0.2.11
+yarl==1.9.2
+zipp==3.16.2