Prepare release for experimental kg creation (#112)

* Update CHANGELOG * Update docs * Update docs * Update CHANGELOG --------- Co-authored-by: Alex Thomas <[email protected]>
neo4j · Sep 3, 2024 · 42aa07c · 42aa07c
1 parent 378c98d
commit 42aa07c
Show file tree

Hide file tree

Showing 9 changed files with 15 additions and 14 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,21 +2,22 @@
 
 ## Next
 
+### Added
+- PDF-to-graph pipeline for knowledge graph construction in experimental mode
+- Introduced support for Component/Pipeline flexible architecture.
+- Added new components for knowledge graph construction, including text splitters, schema builders, entity-relation extractors, and Neo4j writers.
+- Implemented end-to-end tests for the new knowledge graph builder pipeline.
+
 ### Changed
 - When saving the lexical graph in a KG creation pipeline, the document is also saved as a specific node, together with relationships between each chunk and the document they were created from.
 
-## 0.5.0
-
 ### Fixed
 - Corrected the hybrid retriever query to ensure proper normalization of scores in vector search results.
 
 ## 0.4.0
 
 ### Added
 - Add optional custom_prompt arg to the Text2CypherRetriever class.
-- Introduced support for Component/Pipeline flexible architecture.
-- Added new components for knowledge graph construction, including text splitters, schema builders, entity-relation extractors, and Neo4j writers.
-- Implemented end-to-end tests for the new knowledge graph builder pipeline.
 
 ### Changed
 - `GraphRAG.search` method first parameter has been renamed `query_text` (was `query`) for consistency with the retrievers interface.

diff --git a/docs/source/user_guide_kg_builder.rst b/docs/source/user_guide_kg_builder.rst
@@ -60,7 +60,7 @@ They can also be used within a pipeline:
     from neo4j_genai.experimental.components.pdf_loader import PdfLoader
     pipeline = Pipeline()
     my_component = PdfLoader()
-    pipeline.add("component_name", my_component)
+    pipeline.add_component(my_component, "component_name")
 
 
 Document Parser

diff --git a/docs/source/user_guide_pipeline.rst b/docs/source/user_guide_pipeline.rst
@@ -57,8 +57,8 @@ Here's how to create a simple pipeline and propagate results from one component
     from neo4j_genai.experimental.pipeline import Pipeline
 
     pipe = Pipeline()
-    pipe.add_component("a", ComponentAdd())
-    pipe.add_component("b", ComponentAdd())
+    pipe.add_component(ComponentAdd(), "a")
+    pipe.add_component(ComponentAdd(), "b")
 
     pipe.connect("a", "b", {"number2": "a.result"})
     asyncio.run(pipe.run({"a": {"number1": 10, "number2": 1}, "b": {"number1": 4}))

diff --git a/src/neo4j_genai/experimental/components/embedder.py b/src/neo4j_genai/experimental/components/embedder.py
@@ -36,7 +36,7 @@ class TextChunkEmbedder(Component):
         embedder = OpenAIEmbeddings(model="text-embedding-3-large")
         chunk_embedder = TextChunkEmbedder(embedder)
         pipeline = Pipeline()
-        pipeline.add_component("chunk_embedder", chunk_embedder)
+        pipeline.add_component(chunk_embedder, "chunk_embedder")
 
     """
 

diff --git a/src/neo4j_genai/experimental/components/entity_relation_extractor.py b/src/neo4j_genai/experimental/components/entity_relation_extractor.py
@@ -297,7 +297,7 @@ class LLMEntityRelationExtractor(EntityRelationExtractor):
 
         extractor = LLMEntityRelationExtractor(llm=llm)
         pipe = Pipeline()
-        pipe.add_component("extractor", extractor)
+        pipe.add_component(extractor, "extractor")
 
     """
 

diff --git a/src/neo4j_genai/experimental/components/kg_writer.py b/src/neo4j_genai/experimental/components/kg_writer.py
@@ -88,7 +88,7 @@ class Neo4jWriter(KGWriter):
         writer = Neo4jWriter(driver=driver, neo4j_database=DATABASE)
 
         pipeline = Pipeline()
-        pipeline.add_component("writer", writer)
+        pipeline.add_component(writer, "writer")
 
     """
 

diff --git a/src/neo4j_genai/experimental/components/schema.py b/src/neo4j_genai/experimental/components/schema.py
@@ -145,7 +145,7 @@ class SchemaBuilder(Component):
         ]
         pipe = Pipeline()
         schema_builder = SchemaBuilder()
-        pipe.add_component("schema_builder", schema_builder)
+        pipe.add_component(schema_builder, "schema_builder")
         pipe_inputs = {
             "schema": {
                 "entities": entities,

diff --git a/src/neo4j_genai/experimental/components/text_splitters/langchain.py b/src/neo4j_genai/experimental/components/text_splitters/langchain.py
@@ -37,7 +37,7 @@ class LangChainTextSplitterAdapter(TextSplitter):
 
         pipeline = Pipeline()
         text_splitter = LangChainTextSplitterAdapter(RecursiveCharacterTextSplitter())
-        pipeline.add_component("text_splitter", text_splitter)
+        pipeline.add_component(text_splitter, "text_splitter")
 
     """
 

diff --git a/src/neo4j_genai/experimental/components/text_splitters/llamaindex.py b/src/neo4j_genai/experimental/components/text_splitters/llamaindex.py
@@ -37,7 +37,7 @@ class LlamaIndexTextSplitterAdapter(TextSplitter):
 
         pipeline = Pipeline()
         text_splitter = LlamaIndexTextSplitterAdapter(SentenceSplitter())
-        pipeline.add_component("text_splitter", text_splitter)
+        pipeline.add_component(text_splitter, "text_splitter")
 
     """