feat: Qdrant vector storage

.env.example

@@ -71,6 +71,7 @@ VECTOR_SEARCH_PATH="./chromadb"
 #-------------------------------------------------------------------------------
 # Vector Store / Search settings
 #-------------------------------------------------------------------------------
+VECTOR_SEARCH_DATABASE="chroma" # Available options are "chroma", "qdrant"
 VECTOR_SEARCH_COLLECTION_NAME="collection"
 
 VECTOR_SEARCH_SENTENCE_TRANSFORMER_MODEL="intfloat/e5-large-v2" # Can be any Sentence-Transformers compatible model available on Hugging Face
@@ -83,6 +84,24 @@ VECTOR_SEARCH_QUERY_PREFIX="query: " # Can be used to add prefix to text embeddi
 VECTOR_SEARCH_TEXT_SPLITTER_CHUNK_OVERLAP=25 # Determines, for a given chunk of text, how many tokens must overlap with adjacent chunks.
 VECTOR_SEARCH_SEARCH_N_RESULTS=4 # How many entries should the vector search return?
 
+#-------------------------------------------------------------------------------
+# Qdrant settings
+#-------------------------------------------------------------------------------
+# NOTE:
+# - This set of variables allows to configure Qdrant vector storage.
+# - Applicable when "VECTOR_SEARCH_DATABASE" is set to "qdrant".
+# QDRANT_LOCATION="http://localhost:6333"
+# QDRANT_PORT=6333
+# QDRANT_GRPC_PORT=6334
+# QDRANT_PREFER_GRPC=False
+# QDRANT_HTTPS=False
+# QDRANT_URL=
+# QDRANT_API_KEY=
+# QDRANT_PREFIX=
+# QDRANT_TIMEOUT=
+# QDRANT_HOST=
+# QDRANT_PATH=
+
 #-------------------------------------------------------------------------------
 # Basic Rate Limiting
 #-------------------------------------------------------------------------------

pyproject.toml

@@ -28,6 +28,7 @@ scikit-learn = "^1.5.0"
 sentence-transformers = "^3.0.1"
 torch = "^2.3.1"
 warcio = "^1.7.4"
+qdrant-client = "^1.9.1"
 
 [tool.poetry.group.dev.dependencies]
 black = "^24.3.0"