2023-10-27 02:44:30 +00:00
|
|
|
from langchain import hub
|
2023-10-26 01:47:42 +00:00
|
|
|
from langchain.load import dumps, loads
|
2023-10-27 02:44:30 +00:00
|
|
|
from langchain.vectorstores import Pinecone
|
2024-01-02 20:32:16 +00:00
|
|
|
from langchain_community.chat_models import ChatOpenAI
|
|
|
|
|
from langchain_community.embeddings import OpenAIEmbeddings
|
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
|
|
|
from langchain_core.output_parsers import StrOutputParser
|
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel
|
2023-10-27 02:44:30 +00:00
|
|
|
|
2023-10-26 01:47:42 +00:00
|
|
|
|
|
|
|
|
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)
|
2023-10-27 02:44:30 +00:00
|
|
|
|
|
|
|
|
reranked_results = [
|
|
|
|
|
(loads(doc), score)
|
|
|
|
|
for doc, score in sorted(fused_scores.items(), key=lambda x: x[1], reverse=True)
|
|
|
|
|
]
|
|
|
|
|
return reranked_results
|
|
|
|
|
|
2023-10-26 01:47:42 +00:00
|
|
|
|
2023-10-27 02:44:30 +00:00
|
|
|
prompt = hub.pull("langchain-ai/rag-fusion-query-generation")
|
2023-10-26 01:47:42 +00:00
|
|
|
|
2023-10-27 02:44:30 +00:00
|
|
|
generate_queries = (
|
|
|
|
|
prompt | ChatOpenAI(temperature=0) | StrOutputParser() | (lambda x: x.split("\n"))
|
|
|
|
|
)
|
2023-10-26 01:47:42 +00:00
|
|
|
|
|
|
|
|
vectorstore = Pinecone.from_existing_index("rag-fusion", OpenAIEmbeddings())
|
|
|
|
|
retriever = vectorstore.as_retriever()
|
|
|
|
|
|
2023-10-27 02:44:30 +00:00
|
|
|
chain = (
|
|
|
|
|
{"original_query": lambda x: x}
|
|
|
|
|
| generate_queries
|
|
|
|
|
| retriever.map()
|
|
|
|
|
| reciprocal_rank_fusion
|
|
|
|
|
)
|
2023-10-29 05:13:22 +00:00
|
|
|
|
|
|
|
|
# Add typed inputs to chain for playground
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Question(BaseModel):
|
|
|
|
|
__root__: str
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
chain = chain.with_types(input_type=Question)
|
