Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,36 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+vectorstores/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,12 @@
----
-title: Chat Finance Test
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 4.36.1
-app_file: app.py
-pinned: false
----
-
+---
+title: Chat Finance Test
+emoji: 💬
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 4.36.1
+app_file: app.py
+pinned: false
+---
+
 An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

app.py

@@ -1,125 +1,60 @@
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-
-# """
-# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-# """
-# client = InferenceClient("linl03/tinyllama-Fin5k")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     system_message,
-#     max_tokens,
-#     temperature,
-#     top_p,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
-
-#     for val in history:
-#         if val[0]:
-#             messages.append({"role": "user", "content": val[0]})
-#         if val[1]:
-#             messages.append({"role": "assistant", "content": val[1]})
-
-#     messages.append({"role": "user", "content": message})
-
-#     response = ""
-
-#     for message in client.chat_completion(
-#         messages,
-#         max_tokens=max_tokens,
-#         stream=True,
-#         temperature=temperature,
-#         top_p=top_p,
-#     ):
-#         token = message.choices[0].delta.content
-
-#         response += token
-#         yield response
-
-# """
-# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-# """
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-import gradio as gr
-from langchain_community.chat_models import ChatOllama
-from langchain_community.embeddings import GPT4AllEmbeddings
-
-from langchain.prompts import ChatPromptTemplate
-from langchain.schema.runnable import RunnablePassthrough
-from langchain_community.vectorstores import FAISS
-
-vector_db_path = "vectorstores/db_faiss"
-
-# embeddings = OllamaEmbeddings(model="nomic-embed-text", show_progress=False)
-embeddings = GPT4AllEmbeddings(model_name = "all-MiniLM-L6-v2.gguf2.f16.gguf", gpt4all_kwargs = {'allow_download': 'False'})
-
-db = FAISS.load_local(vector_db_path, embeddings, allow_dangerous_deserialization=True)
-
-# # Create retriever
-retriever = db.as_retriever(
-    search_type="similarity",
-    search_kwargs= {"k": 256}
-)
-local_llm = 'alen_ox'
-
-llm = ChatOllama(model=local_llm,
-                 keep_alive="3h", 
-                 max_tokens=512,  
-                 temperature=0)
-
-# Create prompt template
-
-def respond(message, history, system_message, path_document):
-    print(message, history, system_message, path_document)
-    respon = ''
-    print("Answer:\n\n", end=" ", flush=True)
-    template = f"""{system_message}"""+"""
-    {context}
-    Question: {question}
-    """
-    prompt = ChatPromptTemplate.from_template(template)
-
-    rag_chain = (
-        {"context": retriever, "question": RunnablePassthrough()}
-        | prompt
-        | llm
-    )
-    for chunk in rag_chain.stream(message):
-        respon += chunk.content
-        print(chunk.content, end="", flush=True)
-    # print("\n")
-    # return respon
-        yield respon
-    
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="Trả lời câu hỏi CHỈ dựa trên ngữ cảnh sau không có thì bảo không có câu trả lời:", label="System message"),
-        gr.UploadButton("Upload a file", file_count="single"),
-        # gr.DownloadButton("Download the file")
-    ],
-)
-
-if __name__ == "__main__":
+import gradio as gr
+from langchain_community.chat_models import ChatOllama
+from langchain_community.embeddings import GPT4AllEmbeddings
+
+from langchain.prompts import ChatPromptTemplate
+from langchain.schema.runnable import RunnablePassthrough
+from langchain_community.vectorstores import FAISS
+
+vector_db_path = "vectorstores/db_faiss"
+
+# embeddings = OllamaEmbeddings(model="nomic-embed-text", show_progress=False)
+embeddings = GPT4AllEmbeddings(model_name = "all-MiniLM-L6-v2.gguf2.f16.gguf", gpt4all_kwargs = {'allow_download': 'False'})
+
+db = FAISS.load_local(vector_db_path, embeddings, allow_dangerous_deserialization=True)
+
+# # Create retriever
+retriever = db.as_retriever(
+    search_type="similarity",
+    search_kwargs= {"k": 256}
+)
+local_llm = 'alen_ox'
+
+llm = ChatOllama(model=local_llm,
+                 keep_alive="3h", 
+                 max_tokens=512,  
+                 temperature=0)
+
+# Create prompt template
+
+def respond(message, history, system_message, path_document):
+    print(message, history, system_message, path_document)
+    respon = ''
+    print("Answer:\n\n", end=" ", flush=True)
+    template = f"""{system_message}"""+"""
+    {context}
+    Question: {question}
+    """
+    prompt = ChatPromptTemplate.from_template(template)
+
+    rag_chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | prompt
+        | llm
+    )
+    for chunk in rag_chain.stream(message):
+        respon += chunk.content
+        print(chunk.content, end="", flush=True)
+        yield respon
+    
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="Trả lời câu hỏi CHỈ dựa trên ngữ cảnh sau không có thì bảo không có câu trả lời:", label="System message"),
+        gr.UploadButton("Upload a file", file_count="single"),
+        # gr.DownloadButton("Download the file")
+    ],
+)
+
+if __name__ == "__main__":
     demo.launch()

rag_ollama_.py

@@ -0,0 +1,68 @@
+
+
+from langchain_community.chat_models import ChatOllama
+from langchain_community.embeddings import GPT4AllEmbeddings
+
+from langchain.prompts import ChatPromptTemplate
+from langchain.schema.runnable import RunnablePassthrough
+from langchain_community.vectorstores import FAISS
+# from langchain_community.embeddings import GPT4AllEmbeddings
+
+
+# # Create embeddingsclear
+vector_db_path = "vectorstores/db_faiss"
+
+# embeddings = OllamaEmbeddings(model="nomic-embed-text", show_progress=False)
+embeddings = GPT4AllEmbeddings(model_name = "all-MiniLM-L6-v2.gguf2.f16.gguf", gpt4all_kwargs = {'allow_download': 'False'})
+
+db = FAISS.load_local(vector_db_path, embeddings, allow_dangerous_deserialization=True)
+
+
+# # Create retriever
+retriever = db.as_retriever(
+    search_type="similarity",
+    search_kwargs= {"k": 256}
+)
+
+# # Create Ollama language model - Gemma 2
+local_llm = 'alen_ox'
+
+llm = ChatOllama(model=local_llm,
+                 keep_alive="3h", 
+                 max_tokens=512,  
+                 temperature=0)
+
+# Create prompt template
+template = """Trả lời câu hỏi CHỈ dựa trên ngữ cảnh sau không có thì bảo không có câu trả lời:
+{context}
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+# Create the RAG chain using LCEL with prompt printing and streaming output
+rag_chain = (
+    {"context": retriever, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+)
+
+# Function to ask questions
+def ask_question(question):
+    respon = ''
+    print("Answer:\n\n", end=" ", flush=True)
+    for chunk in rag_chain.stream(question):
+        respon += chunk.content
+        print(chunk.content, end="", flush=True)
+    print("\n")
+    return respon
+    # print(rag_chain.invoke(question))
+
+# Example usage
+if __name__ == "__main__":
+    while True:
+        user_question = input("Ask a question (or type 'quit' to exit): ")
+        if user_question.lower() == 'quit':
+            break
+        answer = ask_question(user_question)
+        print(answer)
+        # print("\nFull answer received.\n")

requirements.txt

@@ -1,6 +1,6 @@
-huggingface_hub==0.22.2
-minijinja
-ollama
-langchain_community
-gpt4all
+huggingface_hub==0.22.2
+minijinja
+ollama
+langchain_community
+gpt4all
 faiss-cpu

vectorstores/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:425fb579c21dcf6f3fad4f729c59bf97ccad8ccf5251047ac1bb30a7a0c61751
+size 5904429

vectorstores/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d39be923e9e43a29f16238934c77057e6a5094fc6730966100c434f8ba8fd200
+size 1169768