Upload 5 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
+vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,12 @@
----
-title: Flint FinanceBot
-emoji: 🐢
-colorFrom: indigo
-colorTo: pink
-sdk: gradio
-sdk_version: 4.40.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Flint FinanceBot
+emoji: 🐢
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: 4.40.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,103 @@
+import os
+import gradio as gr
+
+#chatbot
+from langchain.llms import HuggingFacePipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, pipeline
+
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+
+from langchain.prompts import PromptTemplate
+from langchain.chains import RetrievalQA
+
+from textwrap import fill
+
+DATA_PATH='data/'
+DB_FAISS_PATH='vectorstore/db_faiss'
+
+#Call of the model
+model_name = "TheBloke/Llama-2-13b-Chat-GPTQ"
+
+model = AutoModelForCausalLM.from_pretrained(model_name,
+                                             device_map="auto",
+                                             trust_remote_code=True)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
+
+gen_cfg = GenerationConfig.from_pretrained(model_name)
+gen_cfg.max_new_tokens=512
+gen_cfg.temperature=0.0000001 # 0.0
+gen_cfg.return_full_text=True
+gen_cfg.do_sample=True
+gen_cfg.repetition_penalty=1.11
+
+pipe=pipeline(
+    task="text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    generation_config=gen_cfg
+)
+
+
+if gr.NO_RELOAD:
+    llm = HuggingFacePipeline(pipeline=pipe)
+    embeddings = HuggingFaceEmbeddings()
+    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
+    print('todo ok')
+
+
+#st.title('🦜🔗 Flint, your FinanceBot')
+Description="""
+## Finance Bot: Get instant insights from Finance
+
+This chatbot is built using the Retrieval-Augmented Generation (RAG) framework
+            
+"""
+
+
+#DB_FAISS_PATH = os.path.join(local_path, 'vectorstore_docs/db_faiss')
+
+prompt_template = """Use the following pieces of information to answer the user's question.
+    If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+    Context: {context}
+    Question: {question}
+
+    Only return the helpful answer below and nothing else. Try to make it short. Maximum of 500 words.
+    Helpful answer:
+    """
+
+
+prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+Chain_pdf = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    # retriever=db.as_retriever(search_type="similarity_score_threshold", search_kwargs={'k': 5, 'score_threshold': 0.8})
+    # Similarity Search is the default way to retrieve documents relevant to a query, but we can use MMR by setting search_type = "mmr"
+    # k defines how many documents are returned; defaults to 4.
+    # score_threshold allows to set a minimum relevance for documents returned by the retriever, if we are using the "similarity_score_threshold" search type.
+    # return_source_documents=True, # Optional parameter, returns the source documents used to answer the question
+    retriever=db.as_retriever(), # (search_kwargs={'k': 5, 'score_threshold': 0.8}),
+    chain_type_kwargs={"prompt": prompt},
+)
+#query = "When was the solar system formed?"
+#result = Chain_pdf.invoke(query)
+#print(fill(result['result'].strip(), width=100))
+
+
+@spaces.GPU()
+def final_result(query,history, Chain_pdf):
+        result = Chain_pdf.invoke(query)
+        print(fill(result['result'].strip(), width=100))
+        return result
+    
+with gr.Blocks() as demo:
+    system_prompt = gr.Textbox("You are helpful AI.", label="System Prompt")
+    slider = gr.Slider(10, 100, render=False)
+
+    gr.ChatInterface(
+        final_result, additional_inputs=[Chain_pdf]
+    )
+
+demo.launch()

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fc19bf4803c3a8fc2f4a40f914431d612361d838464b3e6cb35bdc0b7c26a9
+size 9008685

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe89076f2d8815f9bf4135cf61398589134f3454d964c5e99b672721c40d6fc
+size 3155250