Merge branch 'main' into main

constants.py

@@ -0,0 +1,11 @@
+from chromadb.config import Settings
+
+# Define the folder for storing database
+PERSIST_DIRECTORY = 'db'
+
+# Define the Chroma settings
+CHROMA_SETTINGS = Settings(
+        chroma_db_impl='duckdb+parquet',
+        persist_directory=PERSIST_DIRECTORY,
+        anonymized_telemetry=False
+)

ingest.py

@@ -3,6 +3,8 @@ from langchain.document_loaders import TextLoader, PDFMinerLoader, CSVLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import Chroma
 from langchain.embeddings import LlamaCppEmbeddings
+from constants import PERSIST_DIRECTORY
+from constants import CHROMA_SETTINGS
 
 def main():
     llama_embeddings_model = os.environ.get('LLAMA_EMBEDDINGS_MODEL')
@@ -23,7 +25,7 @@ def main():
     # Create embeddings
     llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx)
     # Create and store locally vectorstore
-    db = Chroma.from_documents(texts, llama, persist_directory=persist_directory)
+    db = Chroma.from_documents(texts, llama, persist_directory=PERSIST_DIRECTORY, client_settings=CHROMA_SETTINGS)
     db.persist()
     db = None
 

privateGPT.py

@@ -12,10 +12,11 @@ model_type = os.environ.get('MODEL_TYPE')
 model_path = os.environ.get('MODEL_PATH')
 model_n_ctx = os.environ.get('MODEL_N_CTX')
 
+from constants import CHROMA_SETTINGS
+
 def main():
-    # Load stored vectorstore
     llama = LlamaCppEmbeddings(model_path=llama_embeddings_model, n_ctx=model_n_ctx)
-    db = Chroma(persist_directory=persist_directory, embedding_function=llama)
+    db = Chroma(persist_directory=persist_directory, embedding_function=llama, client_settings=CHROMA_SETTINGS)
     retriever = db.as_retriever()
     # Prepare the LLM
     callbacks = [StreamingStdOutCallbackHandler()]

requirements.txt

@@ -1,5 +1,5 @@
-langchain==0.0.162
+langchain==0.0.166
 pygpt4all==1.1.0
 chromadb==0.3.22
-llama-cpp-python==0.1.47
+llama-cpp-python==0.1.48
 urllib3==1.26.6