Fix buggy output from GraphQAChain

[Bearnardd]

fixes #7289
A simple fix of the buggy output of graph_qa. If we have several entities with triplets then the last entry of triplets for a given entity merges with the first entry of the triplets of the next entity.

Example

from langchain.llms import OpenAI
from langchain.indexes import GraphIndexCreator
from langchain.chains import GraphQAChain
from langchain.prompts import PromptTemplate
import os

text = "Apple announced the Vision Pro in 2023."

openai_api_key = os.getenv("OPENAI_API_KEY")

index_creator = GraphIndexCreator(llm=OpenAI(openai_api_key=openai_api_key, temperature=0))
graph = index_creator.from_text(text)
chain = GraphQAChain.from_llm(
    OpenAI(temperature=0, openai_api_key=openai_api_key),
    graph=graph, 
    verbose=True
)

chain.run("When did Apple announce the Vision Pro?")

# output pre-fix
Entities Extracted:
Apple, Vision Pro
Full Context:
Apple announced Vision ProVision Pro was announced in 2023

> Finished chain.

# output post-fix
Entities Extracted:
Apple, Vision Pro
Full Context:
Apple announced Vision Pro
Vision Pro was announced in 2023


> Finished chain.

@baskaryan

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Ignored Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)			Jul 7, 2023 9:11pm

[Bearnardd]

If the output with additional "\n" at the end is somehow problematic we can a add check if the current entity is the last one

[baskaryan]

just so there's not a hanging \n at end of context, maybe:

all_triplets = []
for entity in entities:
  all_triplets.extend(self.graph.get_entity_knowledge(entity))
context = "\n".join(all_triplets)

would be better?

[Bearnardd]

@baskaryan Yeah, way cleaner!

[baskaryan]

thanks @Bearnardd!