v0.1.3

src/indexer.py

@@ -6,6 +6,7 @@ from langchain.embeddings import HuggingFaceBgeEmbeddings
 from langchain.retrievers.self_query.base import SelfQueryRetriever
 from langchain.chains.query_constructor.base import AttributeInfo
 from llm.llmFactory import LLMFactory
+from datetime import datetime
 
 model_name = "BAAI/bge-large-en-v1.5"
 encode_kwargs = {'normalize_embeddings': True} # set True to compute cosine similarity
@@ -102,5 +103,19 @@ retriever = SelfQueryRetriever.from_llm(
     verbose=True
 )
 
+meta_defaults={
+    "date":datetime.now().strftime("%Y-%m-%d %H:%M:%S::%f"),
+    "source":"conversation",
+    "ID":datetime.now().strftime("%Y-%m-%d %H:%M:%S::%f")+"-conversation"
+}
 def getRelevantDocs(query:str):
-    return retriever.get_relevant_documents(query)
+    return retriever.get_relevant_documents(query)
+
+def addText(inStr:str,metadata):
+    md=meta_defaults
+    for key in metadata.keys():
+        md[key]=metadata[key]
+
+    docs = [
+        Document(page_content=inStr, metadata=md)]
+    return vectorstore.add_documents(docs)

src/main.py

@@ -47,6 +47,12 @@ async def get_matching_docs(inStr: str ) -> Any:
     """
     return getRelevantDocs(inStr)
 
+@app.post(api_base+"/addTextDocument")
+async def add_text_document(inStr: str,metadata: Any ) -> Any:
+    """
+     Add text and metadata to the db
+    """
+    return addText(inStr,metadata)