langchain/templates/rag-fusion/rag_fusion/chain.py
Bagatur fa5d49f2c1
docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429)
ran 
```bash
g grep -l "langchain.vectorstores" | xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g"
g grep -l "langchain.document_loaders" | xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g"
g grep -l "langchain.chat_loaders" | xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g"
g grep -l "langchain.document_transformers" | xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g"
g grep -l "langchain\.graphs" | xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g"
g grep -l "langchain\.memory\.chat_message_histories" | xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g"
gco master libs/langchain/tests/unit_tests/*/test_imports.py
gco master libs/langchain/tests/unit_tests/**/test_public_api.py
```
2024-01-02 16:47:11 -05:00

51 lines
1.4 KiB
Python

from langchain import hub
from langchain.load import dumps, loads
from langchain_community.chat_models import ChatOpenAI
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores import Pinecone
from langchain_core.output_parsers import StrOutputParser
from langchain_core.pydantic_v1 import BaseModel
def reciprocal_rank_fusion(results: list[list], k=60):
fused_scores = {}
for docs in results:
# Assumes the docs are returned in sorted order of relevance
for rank, doc in enumerate(docs):
doc_str = dumps(doc)
if doc_str not in fused_scores:
fused_scores[doc_str] = 0
fused_scores[doc_str] += 1 / (rank + k)
reranked_results = [
(loads(doc), score)
for doc, score in sorted(fused_scores.items(), key=lambda x: x[1], reverse=True)
]
return reranked_results
prompt = hub.pull("langchain-ai/rag-fusion-query-generation")
generate_queries = (
prompt | ChatOpenAI(temperature=0) | StrOutputParser() | (lambda x: x.split("\n"))
)
vectorstore = Pinecone.from_existing_index("rag-fusion", OpenAIEmbeddings())
retriever = vectorstore.as_retriever()
chain = (
{"original_query": lambda x: x}
| generate_queries
| retriever.map()
| reciprocal_rank_fusion
)
# Add typed inputs to chain for playground
class Question(BaseModel):
__root__: str
chain = chain.with_types(input_type=Question)