github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-18 21:09:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

community: tigergraph fixes (#20034)

Browse Source 
- added guard on the `pyTigerGraph` import
- added a missed example page in the `docs/integrations/graphs/`
- formatted the `docs/integrations/providers/` page to the consistent
format. Added links.
This commit is contained in:
Leonid Ganeline 2024-04-24 13:49:21 -07:00 committed by GitHub
parent 0186e4e633
commit 13751c3297
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 51 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
docs/docs/integrations/graphs/tigergraph.mdx Normal file
View File

@ -0,0 +1,37 @@
# TigerGraph
>[TigerGraph](https://www.tigergraph.com/tigergraph-db/) is a natively distributed and high-performance graph database.
> The storage of data in a graph format of vertices and edges leads to rich relationships,
> ideal for grouding LLM responses.
A big example of the `TigerGraph` and `LangChain` integration [presented here](https://github.com/tigergraph/graph-ml-notebooks/blob/main/applications/large_language_models/TigerGraph_LangChain_Demo.ipynb).
## Installation and Setup
Follow instructions [how to connect to the `TigerGraph` database](https://docs.tigergraph.com/pytigergraph/current/getting-started/connection).
Install the Python SDK:
```bash
pip install pyTigerGraph
```
## Example
To utilize the `TigerGraph InquiryAI` functionality, you can import `TigerGraph` from `langchain_community.graphs`.
```python
import pyTigerGraph as tg
conn = tg.TigerGraphConnection(host="DATABASE_HOST_HERE", graphname="GRAPH_NAME_HERE", username="USERNAME_HERE", password="PASSWORD_HERE")
### ==== CONFIGURE INQUIRYAI HOST ====
conn.ai.configureInquiryAIHost("INQUIRYAI_HOST_HERE")
from langchain_community.graphs import TigerGraph
graph = TigerGraph(conn)
result = graph.query("How many servers are there?")
print(result)
```

28
docs/docs/integrations/providers/tigergraph.mdx
View File

@ -1,15 +1,13 @@
# TigerGraph # TigerGraph
What is `TigerGraph`? >[TigerGraph](https://www.tigergraph.com/tigergraph-db/) is a natively distributed and high-performance graph database.
> The storage of data in a graph format of vertices and edges leads to rich relationships,
**TigerGraph in a nutshell:** > ideal for grouding LLM responses.
- `TigerGraph` is a natively distributed and high-performance graph database.
- The storage of data in a graph format of vertices and edges leads to rich relationships, ideal for grouding LLM responses.
- Get started quickly with `TigerGraph` by visiting [their website](https://tigergraph.com/).
## Installation and Setup ## Installation and Setup
Follow instructions [how to connect to the `TigerGraph` database](https://docs.tigergraph.com/pytigergraph/current/getting-started/connection).
Install the Python SDK: Install the Python SDK:
```bash ```bash
@ -18,22 +16,10 @@ pip install pyTigerGraph
## Graph store ## Graph store
### TigerGraph Store ### TigerGraph
To utilize the `TigerGraph InquiryAI` functionality, you can import `TigerGraph` from `langchain_community.graphs`. See a [usage example](/docs/integrations/graphs/tigergraph).
```python ```python
import pyTigerGraph as tg
conn = tg.TigerGraphConnection(host="DATABASE_HOST_HERE", graphname="GRAPH_NAME_HERE", username="USERNAME_HERE", password="PASSWORD_HERE")
### ==== CONFIGURE INQUIRYAI HOST ====
conn.ai.configureInquiryAIHost("INQUIRYAI_HOST_HERE")
from langchain_community.graphs import TigerGraph from langchain_community.graphs import TigerGraph
graph = TigerGraph(conn)
result = graph.query("How many servers are there?")
print(result)
``` ```

8
libs/community/langchain_community/graphs/tigergraph_graph.py
View File

@ -39,7 +39,13 @@ class TigerGraph(GraphStore):
return str(self._schema) return str(self._schema)
def set_connection(self, conn: Any) -> None: def set_connection(self, conn: Any) -> None:
from pyTigerGraph import TigerGraphConnection try:
from pyTigerGraph import TigerGraphConnection
except ImportError:
raise ImportError(
"Could not import pyTigerGraph python package. "
"Please install it with `pip install pyTigerGraph`."
)
if not isinstance(conn, TigerGraphConnection): if not isinstance(conn, TigerGraphConnection):
msg = "**conn** parameter must inherit from TigerGraphConnection" msg = "**conn** parameter must inherit from TigerGraphConnection"