Update README.md

README.md

@@ -1,15 +1,10 @@
-# dspy-neo4j-knowledge-graph
+# text-to-cypher
 LLM-driven automated knowledge graph construction from text using DSPy and Neo4j.
 
-![Knowledge Graph](img/kg.png)
-
 ## Project Structure
 ```sh
-dspy-neo4j-knowledge-graph/
+text-to-cypher/
 ├── README.md
-├── examples/
-│   └── wikipedia-abstracts-v0_0_1.ndjson
-├── img/
 ├── main.py
 ├── pyproject.toml
 ├── uv.lock
@@ -79,7 +74,7 @@ MODAIC_TOKEN=<your-modaic-token>
 Run Neo4j locally using Docker:
 ```sh
 docker run \
-    --name dspy-kg \
+    --name text-to-cypher \
     --publish=7474:7474 \
     --publish=7687:7687 \
     --env "NEO4J_AUTH=none" \
@@ -153,8 +148,8 @@ neo4j.query(cypher.statement.replace('```', ''))
 
 ### Stop Neo4j Docker Container
 ```sh
-docker stop dspy-kg
+docker stop text-to-cypher
-docker rm dspy-kg
+docker rm text-to-cypher
 ```
 
 ### Remove Virtual Environment

main.py

@@ -13,25 +13,29 @@ neo4j = Neo4j(
     password=os.getenv("NEO4J_PASSWORD"),
 )
 
-class CypherFromText(dspy.Signature):
+
-    """Instructions:
+class CypherFromQuestion(dspy.Signature):
-    Create a Cypher MERGE statement to model all entities and relationships found in the text following these guidelines:
+    """Task: Generate Cypher statement to query a graph database.
-    - Refer to the provided schema and use existing or similar nodes, properties or relationships before creating new ones.
+    Instructions: Use only the provided relationship types and properties in the schema.
-    - Use generic categories for node and relationship labels."""
+    Do not use any other relationship types or properties that are not provided in the schema.
-    text = dspy.InputField(
+    Do not include any explanations or apologies in your responses.
-        desc="Text to model using nodes, properties and relationships."
+    Do not respond to any questions that might ask anything else than for you to construct a Cypher statement.
+    Do not include any text except the generated Cypher statement.
+    """
+
+    question = dspy.InputField(
+        desc="Question to model using a cypher statement. Use only the provided relationship types and properties in the schema."
     )
     neo4j_schema = dspy.InputField(
         desc="Current graph schema in Neo4j as a list of NODES and RELATIONSHIPS."
     )
-    statement = dspy.OutputField(
+    statement = dspy.OutputField(desc="Cypher statement to query the graph database.")
-        desc="Cypher statement to merge nodes and relationships found in the text."
+
-    )
 
 class GenerateCypherConfig(PrecompiledConfig):
     model: str = "openai/gpt-4o"
     max_tokens: int = 1024
-    
+
 
 class GenerateCypher(PrecompiledProgram):
     config: GenerateCypherConfig
@@ -42,18 +46,20 @@ class GenerateCypher(PrecompiledProgram):
             model=config.model,
             max_tokens=config.max_tokens,
         )
-        self.generate_cypher = dspy.ChainOfThought(CypherFromText)
+        self.generate_cypher = dspy.ChainOfThought(CypherFromQuestion)
         self.generate_cypher.set_lm(self.lm)
-    
+
-    def forward(self, text: str, neo4j_schema: list[str]):
+    def forward(self, question: str, neo4j_schema: list[str]):
-        return self.generate_cypher(text=text, neo4j_schema=neo4j_schema)
+        return self.generate_cypher(question=question, neo4j_schema=neo4j_schema)
+
 
 generate_cypher = GenerateCypher(GenerateCypherConfig())
 
 if __name__ == "__main__":
+    """
     from pathlib import Path
     import json
-    """
+
     examples_path = Path(__file__).parent / "examples" / "wikipedia-abstracts-v0_0_1.ndjson"
     with open(examples_path, "r") as f:
          for line in f:
@@ -67,7 +73,9 @@ if __name__ == "__main__":
     schema = neo4j.fmt_schema()   
     print("SCHEMA:\n", schema)
     """
-    generate_cypher.push_to_hub("farouk1/text-to-cypher", with_code=True, tag="v0.0.6", commit_message="Update README.md")
+    generate_cypher.push_to_hub(
-    
+        "farouk1/text-to-cypher",
-    
+        with_code=True,
-    
+        tag="v0.0.9",
+        commit_message="Update README.md",
+    )

program.json

@@ -4,11 +4,11 @@
     "train": [],
     "demos": [],
     "signature": {
-      "instructions": "Instructions:\nCreate a Cypher MERGE statement to model all entities and relationships found in the text following these guidelines:\n- Refer to the provided schema and use existing or similar nodes, properties or relationships before creating new ones.\n- Use generic categories for node and relationship labels.",
+      "instructions": "Task: Generate Cypher statement to query a graph database.\nInstructions: Use only the provided relationship types and properties in the schema.\nDo not use any other relationship types or properties that are not provided in the schema.\nDo not include any explanations or apologies in your responses.\nDo not respond to any questions that might ask anything else than for you to construct a Cypher statement.\nDo not include any text except the generated Cypher statement.",
       "fields": [
         {
-          "prefix": "Text:",
+          "prefix": "Question:",
-          "description": "Text to model using nodes, properties and relationships."
+          "description": "Question to model using a cypher statement. Use only the provided relationship types and properties in the schema."
         },
         {
           "prefix": "Neo 4 J Schema:",
@@ -20,7 +20,7 @@
         },
         {
           "prefix": "Statement:",
-          "description": "Cypher statement to merge nodes and relationships found in the text."
+          "description": "Cypher statement to query the graph database."
         }
       ]
     },

pyproject.toml

@@ -4,4 +4,4 @@ version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
-dependencies = ["datasets>=4.4.2", "dspy>=3.0.4", "modaic>=0.8.2", "neo4j~=5.18.0", "python-dotenv~=1.0.1"]
+dependencies = ["datasets>=4.4.2", "dspy>=3.0.4", "modaic>=0.8.2", "neo4j~=5.18.0", "python-dotenv~=1.0.1", "sacrebleu>=2.5.1"]