Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

Add docs & some improvements

Tomaz Bratanic1754cbd37d84
diff --git a/docs/api/retrieval_model_clients/Neo4jRM.md b/docs/api/retrieval_model_clients/Neo4jRM.md
new file mode 100644
index 000000000..dc4530f09
--- /dev/null
+++ b/docs/api/retrieval_model_clients/Neo4jRM.md
@@ -0,0 +1,80 @@
+
+# retrieve.neo4j_rm
+
+### Constructor
+
+Initialize an instance of the `Neo4jRM` class.
+
+```python
+Neo4jRM(
+ index_name: str,
+ text_node_property: str,
+ k: int = 5,
+ retrieval_query: str = None,
+ embedding_provider: str = "openai",
+ embedding_model: str = "text-embedding-ada-002",
+)
+```
+
+**Environment Variables:**
+
+You need to define the credentials as environment variables:
+
+- `NEO4J_USERNAME` (_str_): Specifies the username required for authenticating with the Neo4j database. This is a crucial security measure to ensure that only authorized users can access the database.
+
+- `NEO4J_PASSWORD` (_str_): Defines the password associated with the `NEO4J_USERNAME` for authentication purposes. This password should be kept secure to prevent unauthorized access to the database.
+
+- `NEO4J_URI` (_str_): Indicates the Uniform Resource Identifier (URI) used to connect to the Neo4j database. This URI typically includes the protocol, hostname, and port, providing the necessary information to establish a connection to the database.
+
+- `NEO4J_DATABASE` (_str_, optional): Specifies the name of the database to connect to within the Neo4j instance. If not set, the system defaults to using `"neo4j"` as the database name. This allows for flexibility in connecting to different databases within a single Neo4j server.
+
+**Parameters:**
+- `index_name` (_str_): Specifies the name of the vector index to be used within Neo4j for organizing and querying data.
+- `text_node_property` (_str_, _optional_): Defines the specific property of nodes that will be returned.
+- `k` (_int_, _optional_): The number of top results to return from the retrieval operation. It defaults to 5 if not explicitly specified.
+- `retrieval_query` (_str_, _optional_): A custom query string provided for retrieving data. If not provided, a default query tailored to the `text_node_property` will be used.
+- `embedding_provider` (_str_, _optional_): The name of the service provider for generating embeddings. Defaults to "openai" if not specified.
+- `embedding_model` (_str_, _optional_): The specific embedding model to use from the provider. By default, it uses the "text-embedding-ada-002" model from OpenAI.
+
+
+### Methods
+
+#### `forward(self, query: [str], k: Optional[int] = None) -> dspy.Prediction`
+
+Search the neo4j vector index for the top `k` passages matching the given query or queries, using embeddings generated via the specified `embedding_model`.
+
+**Parameters:**
+- `query` (str_): The query.
+- `k` (_Optional[int]_, _optional_): The number of results to retrieve. If not specified, defaults to the value set during initialization.
+
+**Returns:**
+- `dspy.Prediction`: Contains the retrieved passages as a list of string with the prediction signature.
+
+ex:
+```python
+Prediction(
+ passages=['Passage 1 Lorem Ipsum awesome', 'Passage 2 Lorem Ipsum Youppidoo', 'Passage 3 Lorem Ipsum Yassssss']
+)
+```
+
+### Quick Example how to use Neo4j in a local environment.
+
+
+```python
+from dspy.retrieve.neo4j_rm import Neo4jRM
+import os
+
+os.environ["NEO4J_URI"] = 'bolt://localhost:7687'
+os.environ["NEO4J_USERNAME"] = 'neo4j'
+os.environ["NEO4J_PASSWORD"] = 'password'
+
+retriever_model = Neo4jRM(
+ index_name="vector",
+ text_node_property="text"
+)
+
+results = retriever_model("Explore the significance of quantum computing", k=3)
+
+for passage in results.passages:
+ print("Document:", result, "\n")
+```
diff --git a/dspy/retrieve/neo4j_rm.py b/dspy/retrieve/neo4j_rm.py
index 2c5998c49..db0c671ad 100644
--- a/dspy/retrieve/neo4j_rm.py
+++ b/dspy/retrieve/neo4j_rm.py
@@ -56,7 +56,7 @@ class Neo4jRM(dspy.Retrieve):
def __init__(
self,
index_name: str,
- text_node_property: str,
+ text_node_property: str = None,
k: int = 5,
retrieval_query: str = None,
embedding_provider: str = "openai",
@@ -67,7 +67,7 @@ class Neo4jRM(dspy.Retrieve):
self.username = os.getenv("NEO4J_USERNAME")
self.password = os.getenv("NEO4J_PASSWORD")
self.uri = os.getenv("NEO4J_URI")
- self.database = os.getenv("NEO4J_DATABASE")
+ self.database = os.getenv("NEO4J_DATABASE", "neo4j")
self.k = k
self.retrieval_query = retrieval_query
self.text_node_property = text_node_property
@@ -77,6 +77,8 @@ class Neo4jRM(dspy.Retrieve):
raise ValueError("Environment variable NEO4J_PASSWORD must be set")
if not self.uri:
raise ValueError("Environment variable NEO4J_URI must be set")
+ if not self.text_node_property and not self.retrieval_query:
+ raise ValueError("Either `text_node_property` or `retrieval_query` parameters must be defined")
try:
self.driver = GraphDatabase.driver(self.uri, auth=(self.username, self.password))
self.driver.verify_connectivity()
@@ -99,6 +101,7 @@ class Neo4jRM(dspy.Retrieve):
records, _, _ = self.driver.execute_query(
DEFAULT_INDEX_QUERY + retrieval_query,
{"embedding": vector, "index": self.index_name, "k": k or self.k},
+ database_=self.database,
)
contents.extend([dotdict({"long_text": r["text"]}) for r in records])
return contents