update to the latest Document format (#127)

deepset-ai · Dec 20, 2023 · c17ddda · c17ddda
1 parent 65beef5
commit c17ddda
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 10 deletions.
diff --git a/integrations/chroma/example/example.py b/integrations/chroma/example/example.py
@@ -3,7 +3,7 @@
 from pathlib import Path
 
 from haystack import Pipeline
-from haystack.components.file_converters import TextFileToDocument
+from haystack.components.converters import TextFileToDocument
 from haystack.components.writers import DocumentWriter
 
 from chroma_haystack import ChromaDocumentStore
@@ -19,11 +19,11 @@
 indexing.add_component("converter", TextFileToDocument())
 indexing.add_component("writer", DocumentWriter(document_store))
 indexing.connect("converter", "writer")
-indexing.run({"converter": {"paths": file_paths}})
+indexing.run({"converter": {"sources": file_paths}})
 
 querying = Pipeline()
 querying.add_component("retriever", ChromaQueryRetriever(document_store))
 results = querying.run({"retriever": {"queries": ["Variable declarations"], "top_k": 3}})
 
-for d in results["retriever"][0]:
-    print(d.metadata, d.score)
+for d in results["retriever"]["documents"][0]:
+    print(d.meta, d.score)
diff --git a/integrations/chroma/src/chroma_haystack/document_store.py b/integrations/chroma/src/chroma_haystack/document_store.py
@@ -247,10 +247,6 @@ def _normalize_filters(self, filters: Dict[str, Any]) -> Tuple[List[str], Dict[s
                 # if the list contains multiple items, we need an $or chain
                 for v in value:
                     where["$or"].append({field: v})
-            elif field == "mime_type":
-                # Schedule for removal the original key, we're going to change it
-                keys_to_remove.append(field)
-                where["_mime_type"] = value
 
         for k in keys_to_remove:
             del filters[k]
@@ -310,8 +306,7 @@ def _query_result_to_documents(self, result: QueryResult) -> List[List[Document]
 
                 # prepare metadata
                 if metadatas := result.get("metadatas"):
-                    document_dict["metadata"] = dict(metadatas[i][j])
-                    document_dict["mime_type"] = document_dict["metadata"].pop("_mime_type")
+                    document_dict["meta"] = dict(metadatas[i][j])
 
                 if embeddings := result.get("embeddings"):
                     document_dict["embedding"] = np.array(embeddings[i][j])