Update README.md

README.md

@@ -21,6 +21,67 @@ Dataset: neo4j/text2cypher-2024v1
 
 An overview of the finetuned models and benchmarking results are shared at https://medium.com/p/d77be96ab65a and https://medium.com/p/b2203d1173b0
 
+## Example Cypher generation
+`python
+import openai
+
+# Define the instruction and helper functions
+instruction = (
+    "Generate Cypher statement to query a graph database. "
+    "Use only the provided relationship types and properties in the schema. \n"
+    "Schema: {schema} \n Question: {question}  \n Cypher output: "
+)
+
+def prepare_chat_prompt(question, schema):
+    # Build the messages list for the OpenAI API
+    return [
+        {
+            "role": "user",
+            "content": instruction.format(schema=schema, question=question),
+        }
+    ]
+
+def _postprocess_output_cypher(output_cypher: str) -> str:
+    # Remove any explanation text and code block markers
+    partition_by = "**Explanation:**"
+    output_cypher, _, _ = output_cypher.partition(partition_by)
+    output_cypher = output_cypher.strip("`\n")
+    output_cypher = output_cypher.lstrip("cypher\n")
+    output_cypher = output_cypher.strip("`\n ")
+    return output_cypher
+
+# Configure the OpenAI API endpoint to your Ollama server.
+# (Adjust the API base URL if your Ollama server is hosted at a different address/port.)
+openai.api_base = "http://localhost:11434/v1"
+openai.api_key = "YOUR_API_KEY"  # Include if your setup requires an API key
+
+# Set the model name as used by Ollama (this should match the name configured on your Ollama server)
+model_name = "avinashm/text2cypher"
+
+# Define the question and schema
+question = "What are the movies of Tom Hanks?"
+schema = "(:Actor)-[:ActedIn]->(:Movie)"
+
+# Prepare the conversation messages
+messages = prepare_chat_prompt(question=question, schema=schema)
+
+# Call the API using similar generation parameters to your original script.
+response = openai.ChatCompletion.create(
+    model=model_name,
+    messages=messages,
+    temperature=0.2,
+    max_tokens=512,   # equivalent to max_new_tokens in your original script
+    top_p=0.9,
+)
+
+# Extract and post-process the output
+raw_output = response["choices"][0]["message"]["content"]
+output = _postprocess_output_cypher(raw_output)
+
+print(output)
+`
+
+
 
 ## Bias, Risks, and Limitations