Removed not used files and corrected the function calls in retriever …

…component
opea-project · Aug 7, 2024 · 4224709 · 4224709
1 parent c6d5a96
commit 4224709
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/comps/dataprep/pinecone/data/nke-10k-2023.pdf b/comps/dataprep/pinecone/data/nke-10k-2023.pdf
diff --git a/comps/retrievers/langchain/pinecone/ingest.py b/comps/retrievers/langchain/pinecone/ingest.py
@@ -63,7 +63,7 @@ def ingest_documents():
     contains Edgar 10k filings data for Nike."""
     # Load list of pdfs
     company_name = "Nike"
-    data_path = "../data/"
+    data_path = "data/"
     doc_path = [os.path.join(data_path, file) for file in os.listdir(data_path)][0]
 
     print("Parsing 10k filing doc for NIKE", doc_path)

diff --git a/comps/retrievers/langchain/pinecone/retriever_pinecone.py b/comps/retrievers/langchain/pinecone/retriever_pinecone.py
@@ -55,12 +55,12 @@ def retrieve(input: EmbedDoc) -> SearchedDoc:
         if input.distance_threshold is None:
             raise ValueError("distance_threshold must be provided for " + "similarity_distance_threshold retriever")
         docs_and_similarities = vector_db.similarity_search_by_vector_with_score(
-            embedding=input.embedding, k=input.k, distance_threshold=input.distance_threshold
+            embedding=input.embedding, k=input.k
         )
         search_res = [doc for doc, similarity in docs_and_similarities if similarity > input.distance_threshold]
     elif input.search_type == "similarity_score_threshold":
         docs_and_similarities = vector_db.similarity_search_by_vector_with_score(
-            query=input.text, k=input.k, score_threshold=input.score_threshold
+            query=input.text, k=input.k
         )
         search_res = [doc for doc, similarity in docs_and_similarities if similarity > input.score_threshold]
     elif input.search_type == "mmr":