yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-08-26 09:26:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

initial (#6355)

Browse Source
This commit is contained in:
Timo Moeller 2023-11-23 10:32:54 +01:00 committed by GitHub
parent cfff0d5212
commit b34c35d982
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 81 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
examples/preview/retrievers/in_memory_bm25_documentsearch.py Normal file
View File

@ -0,0 +1,28 @@
from haystack.preview import Document
from haystack.preview.components.retrievers import InMemoryBM25Retriever
from haystack.preview.document_stores import InMemoryDocumentStore
from haystack.preview.pipeline import Pipeline
# Create components and a query pipeline
document_store = InMemoryDocumentStore()
retriever = InMemoryBM25Retriever(document_store=document_store)
pipeline = Pipeline()
pipeline.add_component(instance=retriever, name="retriever")
# Add Documents
documents = [
Document(content="There are over 7,000 languages spoken around the world today."),
Document(
content="Elephants have been observed to behave in a way that indicates a high level of self-awareness, such as recognizing themselves in mirrors."
),
Document(
content="In certain parts of the world, like the Maldives, Puerto Rico, and San Diego, you can witness the phenomenon of bioluminescent waves."
),
]
document_store.write_documents(documents)
# Run the pipeline
result = pipeline.run(data={"retriever": {"query": "How many languages are there?"}})
print(result["retriever"]["documents"][0])

53
examples/preview/retrievers/in_memory_bm25_rag.py Normal file
View File

@ -0,0 +1,53 @@
import os
from haystack.preview import Document
from haystack.preview import Pipeline
from haystack.preview.components.builders.answer_builder import AnswerBuilder
from haystack.preview.components.builders.prompt_builder import PromptBuilder
from haystack.preview.components.generators import GPTGenerator
from haystack.preview.components.retrievers import InMemoryBM25Retriever
from haystack.preview.document_stores import InMemoryDocumentStore
# Create a RAG query pipeline
prompt_template = """
Given these documents, answer the question.\nDocuments:
{% for doc in documents %}
{{ doc.content }}
{% endfor %}
\nQuestion: {{question}}
\nAnswer:
"""
rag_pipeline = Pipeline()
rag_pipeline.add_component(instance=InMemoryBM25Retriever(document_store=InMemoryDocumentStore()), name="retriever")
rag_pipeline.add_component(instance=PromptBuilder(template=prompt_template), name="prompt_builder")
rag_pipeline.add_component(instance=GPTGenerator(api_key=os.environ.get("OPENAI_API_KEY")), name="llm")
rag_pipeline.add_component(instance=AnswerBuilder(), name="answer_builder")
rag_pipeline.connect("retriever", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "llm")
rag_pipeline.connect("llm.replies", "answer_builder.replies")
rag_pipeline.connect("llm.metadata", "answer_builder.metadata")
rag_pipeline.connect("retriever", "answer_builder.documents")
# Draw the pipeline
rag_pipeline.draw("./rag_pipeline.png")
# Add Documents
documents = [
Document(content="There are over 7,000 languages spoken around the world today."),
Document(
content="Elephants have been observed to behave in a way that indicates a high level of self-awareness, such as recognizing themselves in mirrors."
),
Document(
content="In certain parts of the world, like the Maldives, Puerto Rico, and San Diego, you can witness the phenomenon of bioluminescent waves."
),
]
rag_pipeline.get_component("retriever").document_store.write_documents(documents)
# Run the pipeline
question = "How many languages are there?"
result = rag_pipeline.run(
{"retriever": {"query": question}, "prompt_builder": {"question": question}, "answer_builder": {"query": question}}
)
print(result["answer_builder"]["answers"][0])