update required packages

Author: wzdavid

.gitignore

@@ -11,6 +11,14 @@ storage/
 # Test files
 test_*.*
 
+# Python venv
+.venv/
+bin/
+include/
+lib/
+pyvenv.cfg
+etc/
+
 # The following are ignored by default.
 
 # Byte-compiled / optimized / DLL files

config.py

@@ -126,7 +126,4 @@
 DEV_MODE = THINKRAG_ENV == "development"
 
 # For creating IndexManager
-DEFAULT_INDEX_NAME = "knowledge_base"
-
-# NLTK model storage path, default to be 'localmodels/nltk', under the project root directory, used for the unstructured library
-NLTK_DATA_PATH = os.path.join(os.getcwd(), MODEL_DIR, "nltk_data")
+DEFAULT_INDEX_NAME = "knowledge_base"

docs/HowToUsePythonVirtualEnv.md

@@ -0,0 +1,35 @@
+# Create an environment with venv and installing Streamlit and other packages with pip.
+# Refer to: https://docs.streamlit.io/get-started/installation/command-line
+### 1. Open a terminal and navigate to your project folder
+```zsh
+cd ThinkRAG
+```
+### 2. In your terminal, type:
+```zsh
+python -m venv .venv
+```
+A folder named ".venv" will appear in your project. This directory is where your virtual environment and its dependencies are installed.
+### 3. Activate your environment with one of the following commands
+```zsh
+# Windows command prompt
+.venv\Scripts\activate.bat
+
+# Windows PowerShell
+.venv\Scripts\Activate.ps1
+
+# macOS and Linux
+source .venv/bin/activate
+```
+Once activated, you will see your environment name in parentheses before your prompt. "(.venv)"
+### 4. In the terminal with your environment activated, install all required packages:
+```zsh
+pip3 install -r requirements.txt
+```
+### 5. Run your Streamlit app
+```zsh
+python3 -m streamlit run app.py
+```
+### 6. When you're done using this environment, return to your normal shell by typing:
+```zsh
+deactivate
+```

requirements.txt

@@ -1,32 +1,18 @@
-chardet
-chromadb
-docx2txt
-jieba
-langchain
-langchain_openai 
-llama-index
-llama-index-embeddings-huggingface
-llama-index-embeddings-langchain
-llama-index-llms-langchain
-llama-index-readers-web
-llama-index-retrievers-bm25
-llama-index-storage-kvstore-redis
-llama-index-vector-stores-chroma
-llama-index-vector-stores-elasticsearch
-llama-index-vector-stores-lancedb
-llama-index-llms-ollama
-llama-index-storage-chat_store-redis
-ollama
-Pillow
-python-pptx 
-redis
-requests
-sentence-transformers
-spacy
-sse-starlette
-streamlit
-streamlit-aggrid
-torch 
-transformers 
-unstructured
-uvicorn
+llama_index==0.11.19
+streamlit==1.39.0
+langchain==0.3.4
+langchain-community==0.3.3
+langchain_openai==0.2.3
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-langchain==0.2.1
+llama-index-llms-langchain==0.4.2
+llama-index-readers-web==0.2.4
+llama-index-retrievers-bm25==0.4.0
+llama-index-storage-kvstore-redis==0.2.0
+llama-index-vector-stores-chroma==0.2.1
+llama-index-vector-stores-elasticsearch==0.3.3
+llama-index-vector-stores-lancedb==0.2.4
+llama-index-llms-ollama==0.3.4
+llama-index-storage-chat_store-redis==0.3.2
+llama_index.storage.docstore.redis==0.2.0
+llama_index.storage.index_store.redis==0.3.0