Updated the variable names within the for-loop to differentiate betwe… (#1356)

* Updated the variable names within the for-loop to differentiate between them and the original title variable used in the dataframe. This avoids corrupting the original column-name defined in the title variable.

* Semver and formart

---------

Co-authored-by: Gabriel Nieves-Ponce <[email protected]>
Co-authored-by: Alonso Guevara <[email protected]>

Author: 3 people

.semversioner/next-release/patch-20241105172851917088.json

@@ -0,0 +1,4 @@
+{
+  "type": "patch",
+  "description": "Fix embeddings faulty assignments"
+}

graphrag/index/operations/embed_text/embed_text.py

@@ -193,14 +193,16 @@ async def _text_embed_with_vector_store(
 
         vectors = result.embeddings or []
         documents: list[VectorStoreDocument] = []
-        for id, text, title, vector in zip(ids, texts, titles, vectors, strict=True):
-            if type(vector) is np.ndarray:
-                vector = vector.tolist()
+        for doc_id, doc_text, doc_title, doc_vector in zip(
+            ids, texts, titles, vectors, strict=True
+        ):
+            if type(doc_vector) is np.ndarray:
+                doc_vector = doc_vector.tolist()
             document = VectorStoreDocument(
-                id=id,
-                text=text,
-                vector=vector,
-                attributes={"title": title},
+                id=doc_id,
+                text=doc_text,
+                vector=doc_vector,
+                attributes={"title": doc_title},
             )
             documents.append(document)