feat: add dele folder

appold.py

@@ -1,78 +0,0 @@
-import os
-import gradio as gr
-import copy
-import time
-import llama_cpp
-import ingest
-from llama_cpp import Llama
-from huggingface_hub import hf_hub_download  
-
-import run_localGPT_API
-
-
-llm = Llama(
-    model_path=hf_hub_download(
-        repo_id=os.environ.get("REPO_ID", "TheBloke/Llama-2-7b-Chat-GGUF"),
-        filename=os.environ.get("MODEL_FILE", "llama-2-7b-chat.Q4_K_M.gguf"),
-    ),
-    n_ctx=2048,
-    n_gpu_layers=50, # change n_gpu_layers if you have more or less VRAM 
-) 
-
-history = []
-
-system_message = """
-you are a helpful, respectful and honest assistant. you should only respond to the following topics: water, climate, global warming, NASA data and geography. Always answer in the most helpful and safe way possible.  Your answers should not include harmful, unethical, racist, sexist, toxic, dangerous or illegal content. Make sure that your answers are socially unbiased and positive in nature, as well as sticking to the topics of water, climate, global warming, NASA data and geography.
-If a question doesn't make sense or isn't factually coherent, explain that only questions on the topics of water, climate, global warming, NASA data and geography are accepted. If you don't know the answer to a question, don't share false information.
-"""
-
-
-def generate_text(message, history):
-    temp = ""
-    input_prompt = f"[INST] <<SYS>>\n{system_message}\n<</SYS>>\n\n "
-    for interaction in history:
-        input_prompt = input_prompt + str(interaction[0]) + " [/INST] " + str(interaction[1]) + " </s><s> [INST] "
-
-    input_prompt = input_prompt + str(message) + " [/INST] "
-
-    output = llm(
-        input_prompt,
-        temperature=0.15,
-        top_p=0.1,
-        top_k=40, 
-        repeat_penalty=1.1,
-        max_tokens=1024,
-        stop=[
-            "<|prompter|>",
-            "<|endoftext|>",
-            "<|endoftext|> \n",
-            "ASSISTANT:",
-            "USER:",
-            "SYSTEM:",
-        ],
-        stream=True,
-    )
-    for out in output:
-        stream = copy.deepcopy(out)
-        temp += stream["choices"][0]["text"]
-        yield temp
-
-    history = ["init", input_prompt]
-
-
-demo = gr.ChatInterface(
-    generate_text,
-    title="Katara LLM",
-    description="LLM of project https://katara.earth/",
-    examples=["Show me all about water"],
-    cache_examples=True,
-    retry_btn=None,
-    undo_btn="Delete Previous",
-    clear_btn="Clear",
-)
-demo.queue(concurrency_count=1, max_size=5)
-
-demo.launch()
-
-ingest.main()
-run_localGPT_API.main()

appv1.py

@@ -1,183 +0,0 @@
-import logging
-import os
-import shutil
-import subprocess
-
-import torch
-from flask import Flask, jsonify, request, render_template
-from langchain.chains import RetrievalQA
-from langchain.embeddings import HuggingFaceInstructEmbeddings
-
-# from langchain.embeddings import HuggingFaceEmbeddings
-from run_localGPT import load_model
-from prompt_template_utils import get_prompt_template
-
-# from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.vectorstores import Chroma
-from werkzeug.utils import secure_filename
-
-from constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME
-
-if torch.backends.mps.is_available():
-    DEVICE_TYPE = "mps"
-elif torch.cuda.is_available():
-    DEVICE_TYPE = "cuda"
-else:
-    DEVICE_TYPE = "cpu"
-
-SHOW_SOURCES = True
-
-EMBEDDINGS = HuggingFaceInstructEmbeddings(model_name=EMBEDDING_MODEL_NAME, model_kwargs={"device": DEVICE_TYPE})
-
-# uncomment the following line if you used HuggingFaceEmbeddings in the ingest.py
-# EMBEDDINGS = HuggingFaceEmbeddings(model_name=EMBEDDING_MODEL_NAME)
-# if os.path.exists(PERSIST_DIRECTORY):
-#     try:
-#         shutil.rmtree(PERSIST_DIRECTORY)
-#     except OSError as e:
-#         print(f"Error: {e.filename} - {e.strerror}.")
-# else:
-#     print("The directory does not exist")
-
-# run_langest_commands = ["python", "ingest.py"]
-# if DEVICE_TYPE == "cpu":
-#     run_langest_commands.append("--device_type")
-#     run_langest_commands.append(DEVICE_TYPE)
-
-# result = subprocess.run(run_langest_commands, capture_output=True)
-# if result.returncode != 0:
-#     raise FileNotFoundError(
-#         "No files were found inside SOURCE_DOCUMENTS, please put a starter file inside before starting the API!"
-#     )
-
-# load the vectorstore
-DB = Chroma(
-    persist_directory=PERSIST_DIRECTORY,
-    embedding_function=EMBEDDINGS,
-    client_settings=CHROMA_SETTINGS,
-)
-
-RETRIEVER = DB.as_retriever()
-
-LLM = load_model(device_type=DEVICE_TYPE, model_id=MODEL_ID, model_basename=MODEL_BASENAME)
-prompt, memory = get_prompt_template(promptTemplate_type="llama", history=False)
-
-QA = RetrievalQA.from_chain_type(
-    llm=LLM,
-    chain_type="stuff",
-    retriever=RETRIEVER,
-    return_source_documents=SHOW_SOURCES,
-    chain_type_kwargs={
-        "prompt": prompt,
-    },
-)
-
-app = Flask(__name__)
-
-@app.route("/")
-def index():
-    return render_template("home.html")
-
-
-@app.route("/api/delete_source", methods=["GET"])
-def delete_source_route():
-    folder_name = "SOURCE_DOCUMENTS"
-
-    if os.path.exists(folder_name):
-        shutil.rmtree(folder_name)
-
-    os.makedirs(folder_name)
-
-    return jsonify({"message": f"Folder '{folder_name}' successfully deleted and recreated."})
-
-
-@app.route("/api/save_document", methods=["GET", "POST"])
-def save_document_route():
-    if "document" not in request.files:
-        return "No document part", 400
-    file = request.files["document"]
-    if file.filename == "":
-        return "No selected file", 400
-    if file:
-        filename = secure_filename(file.filename)
-        folder_path = "SOURCE_DOCUMENTS"
-        if not os.path.exists(folder_path):
-            os.makedirs(folder_path)
-        file_path = os.path.join(folder_path, filename)
-        file.save(file_path)
-        return "File saved successfully", 200
-
-
-@app.route("/api/run_ingest", methods=["GET"])
-def run_ingest_route():
-    global DB
-    global RETRIEVER
-    global QA
-    try:
-        if os.path.exists(PERSIST_DIRECTORY):
-            try:
-                shutil.rmtree(PERSIST_DIRECTORY)
-            except OSError as e:
-                print(f"Error: {e.filename} - {e.strerror}.")
-        else:
-            print("The directory does not exist")
-
-        run_langest_commands = ["python", "ingest.py"]
-        if DEVICE_TYPE == "cpu":
-            run_langest_commands.append("--device_type")
-            run_langest_commands.append(DEVICE_TYPE)
-
-        result = subprocess.run(run_langest_commands, capture_output=True)
-        if result.returncode != 0:
-            return "Script execution failed: {}".format(result.stderr.decode("utf-8")), 500
-        # load the vectorstore
-        DB = Chroma(
-            persist_directory=PERSIST_DIRECTORY,
-            embedding_function=EMBEDDINGS,
-            client_settings=CHROMA_SETTINGS,
-        )
-        RETRIEVER = DB.as_retriever()
-        prompt, memory = get_prompt_template(promptTemplate_type="llama", history=False)
-
-        QA = RetrievalQA.from_chain_type(
-            llm=LLM,
-            chain_type="stuff",
-            retriever=RETRIEVER,
-            return_source_documents=SHOW_SOURCES,
-            chain_type_kwargs={
-                "prompt": prompt,
-            },
-        )
-        return "Script executed successfully: {}".format(result.stdout.decode("utf-8")), 200
-    except Exception as e:
-        return f"Error occurred: {str(e)}", 500
-
-
-@app.route("/api/prompt_route", methods=["GET", "POST"])
-def prompt_route():
-    global QA
-    user_prompt = request.form.get("user_prompt")
-    if user_prompt:
-        # print(f'User Prompt: {user_prompt}')
-        # Get the answer from the chain
-        res = QA(user_prompt)
-        answer, docs = res["result"], res["source_documents"]
-
-        prompt_response_dict = {
-            "Prompt": user_prompt,
-            "Answer": answer,
-        }
-
-        prompt_response_dict["Sources"] = []
-        for document in docs:
-            prompt_response_dict["Sources"].append(
-                (os.path.basename(str(document.metadata["source"])), str(document.page_content))
-            )
-
-        return jsonify(prompt_response_dict), 200
-    else:
-        return "No user prompt received", 400
-
-
-if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=5110)

constants.py

@@ -11,8 +11,10 @@ from langchain.document_loaders import UnstructuredFileLoader
 # load_dotenv()
 ROOT_DIRECTORY = os.path.dirname(os.path.realpath(__file__))
 
+PATH_NAME_SOURCE_DIRECTORY = "SOURCE_DOCUMENTS"
+
 # Define the folder for storing database
-SOURCE_DIRECTORY = f"{ROOT_DIRECTORY}/SOURCE_DOCUMENTS"
+SOURCE_DIRECTORY = f"{ROOT_DIRECTORY}/{PATH_NAME_SOURCE_DIRECTORY}"
 
 PERSIST_DIRECTORY = f"{ROOT_DIRECTORY}/DB"
 

main.py

@@ -6,7 +6,6 @@ from pydantic import BaseModel
 import os
 import shutil
 import subprocess
-import shutil
 
 # import torch
 from langchain.chains import RetrievalQA
@@ -20,7 +19,7 @@ from prompt_template_utils import get_prompt_template
 # from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.vectorstores import Chroma
 
-from constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME
+from constants import CHROMA_SETTINGS, EMBEDDING_MODEL_NAME, PERSIST_DIRECTORY, MODEL_ID, MODEL_BASENAME, PATH_NAME_SOURCE_DIRECTORY
 
 # if torch.backends.mps.is_available():
 #     DEVICE_TYPE = "mps"
@@ -179,11 +178,10 @@ async def create_upload_file(file: UploadFile):
     # move the cursor back to the beginning
     await file.seek(0)
 
-    if file_size > 2 * 1024 * 1024:
-        # more than 2 MB
+    if file_size > 10 * 1024 * 1024:
+        # more than 10 MB
         raise HTTPException(status_code=400, detail="File too large")
 
-    # check the content type (MIME type)
     content_type = file.content_type
 
     if content_type not in [
@@ -200,7 +198,15 @@ async def create_upload_file(file: UploadFile):
         "application/x-python-code"]:
         raise HTTPException(status_code=400, detail="Invalid file type")
 
-    # do something with the valid file
+    upload_dir = os.path.join(os.getcwd(), PATH_NAME_SOURCE_DIRECTORY)
+    if not os.path.exists(upload_dir):
+        os.makedirs(upload_dir)
+
+    dest = os.path.join(upload_dir, file.filename)
+
+    with open(dest, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+
     return {"filename": file.filename}
 # async def create_upload_file(file: Union[UploadFile, None] = None):
 #     try: