Example/cleaning (#196)

* Remove 'old' folder - add example for Ollama LLM

* Update examples' README

* Explicitly set 'return_context' to prevent warnings in examples

Author: stellasia

examples/README.md

@@ -67,7 +67,7 @@ are listed in [the last section of this file](#customize).
 - [MistralAI](./customize/llms/mistalai_llm.py)
 - [Cohere](./customize/llms/cohere_llm.py)
 - [Anthropic (Claude)](./customize/llms/anthropic_llm.py)
-- [Ollama]()
+- [Ollama](./customize/llms/ollama_llm.py)
 - [Custom LLM](./customize/llms/custom_llm.py)
 
 
@@ -91,6 +91,7 @@ are listed in [the last section of this file](#customize).
 
 - [End to end example with explicit components and text input](./customize/build_graph/pipeline/kg_builder_from_text.py)
 - [End to end example with explicit components and PDF input](./customize/build_graph/pipeline/kg_builder_from_pdf.py)
+- [Process multiple documents](./customize/build_graph/pipeline/kg_builder_two_documents_entity_resolution.py)
 
 #### Components
 

examples/customize/answer/custom_prompt.py

@@ -54,7 +54,10 @@
 
 rag = GraphRAG(retriever=retriever, llm=llm, prompt_template=template)
 
-result = rag.search("Tell me more about Avatar movies")
+result = rag.search(
+    "Tell me more about Avatar movies",
+    return_context=True,
+)
 print(result.answer)
 
 driver.close()

examples/customize/answer/langchain_compatiblity.py

@@ -40,7 +40,10 @@
     llm=llm,  # type: ignore[arg-type, unused-ignore]
 )
 
-result = rag.search("Tell me more about Avatar movies")
+result = rag.search(
+    "Tell me more about Avatar movies",
+    return_context=False,
+)
 print(result.answer)
 
 driver.close()

examples/old/pipeline/kg_builder_two_documents_entity_resolution.py renamed to examples/customize/build_graph/pipeline/kg_builder_two_documents_entity_resolution.py

@@ -0,0 +1,12 @@
+from neo4j_graphrag.llm import LLMResponse, OpenAILLM
+
+# not used but needs to be provided
+api_key = "ollama"
+
+llm = OpenAILLM(
+    base_url="http://localhost:11434/v1",
+    model_name="<model_name>",
+    api_key=api_key,
+)
+res: LLMResponse = llm.invoke("What is the additive color model?")
+print(res.content)

examples/customize/llms/ollama_llm.py

@@ -52,7 +52,11 @@ def formatter(record: neo4j.Record) -> RetrieverResultItem:
 
 rag = GraphRAG(retriever=retriever, llm=llm)
 
-result = rag.search("Tell me more about Avatar movies")
+result = rag.search(
+    "Tell me more about Avatar movies",
+    return_context=True,
+)
 print(result.answer)
+# print(result.retriever_result)
 
 driver.close()