mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
9ffca3b92a
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'
```
92 lines
2.7 KiB
Python
92 lines
2.7 KiB
Python
import os
|
|
|
|
from langchain.chat_models import ChatOpenAI
|
|
from langchain.embeddings import OpenAIEmbeddings
|
|
from langchain.prompts import ChatPromptTemplate
|
|
from langchain.vectorstores import MongoDBAtlasVectorSearch
|
|
from langchain_core.documents import Document
|
|
from langchain_core.output_parsers import StrOutputParser
|
|
from langchain_core.pydantic_v1 import BaseModel
|
|
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
|
|
from pymongo import MongoClient
|
|
|
|
MONGO_URI = os.environ["MONGO_URI"]
|
|
PARENT_DOC_ID_KEY = "parent_doc_id"
|
|
# Note that if you change this, you also need to change it in `rag_mongo/chain.py`
|
|
DB_NAME = "langchain-test-2"
|
|
COLLECTION_NAME = "test"
|
|
ATLAS_VECTOR_SEARCH_INDEX_NAME = "default"
|
|
EMBEDDING_FIELD_NAME = "embedding"
|
|
client = MongoClient(MONGO_URI)
|
|
db = client[DB_NAME]
|
|
MONGODB_COLLECTION = db[COLLECTION_NAME]
|
|
|
|
|
|
vector_search = MongoDBAtlasVectorSearch.from_connection_string(
|
|
MONGO_URI,
|
|
DB_NAME + "." + COLLECTION_NAME,
|
|
OpenAIEmbeddings(disallowed_special=()),
|
|
index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
|
|
)
|
|
|
|
|
|
def retrieve(query: str):
|
|
results = vector_search.similarity_search(
|
|
query,
|
|
k=4,
|
|
pre_filter={"doc_level": {"$eq": "child"}},
|
|
post_filter_pipeline=[
|
|
{"$project": {"embedding": 0}},
|
|
{
|
|
"$lookup": {
|
|
"from": COLLECTION_NAME,
|
|
"localField": PARENT_DOC_ID_KEY,
|
|
"foreignField": PARENT_DOC_ID_KEY,
|
|
"as": "parent_context",
|
|
"pipeline": [
|
|
{"$match": {"doc_level": "parent"}},
|
|
{"$limit": 1},
|
|
{"$project": {"embedding": 0}},
|
|
],
|
|
}
|
|
},
|
|
],
|
|
)
|
|
parent_docs = []
|
|
parent_doc_ids = set()
|
|
for result in results:
|
|
res = result.metadata["parent_context"][0]
|
|
text = res.pop("text")
|
|
# This causes serialization issues.
|
|
res.pop("_id")
|
|
parent_doc = Document(page_content=text, metadata=res)
|
|
if parent_doc.metadata[PARENT_DOC_ID_KEY] not in parent_doc_ids:
|
|
parent_doc_ids.add(parent_doc.metadata[PARENT_DOC_ID_KEY])
|
|
parent_docs.append(parent_doc)
|
|
return parent_docs
|
|
|
|
|
|
# RAG prompt
|
|
template = """Answer the question based only on the following context:
|
|
{context}
|
|
Question: {question}
|
|
"""
|
|
prompt = ChatPromptTemplate.from_template(template)
|
|
|
|
# RAG
|
|
model = ChatOpenAI()
|
|
chain = (
|
|
RunnableParallel({"context": retrieve, "question": RunnablePassthrough()})
|
|
| prompt
|
|
| model
|
|
| StrOutputParser()
|
|
)
|
|
|
|
|
|
# Add typing for input
|
|
class Question(BaseModel):
|
|
__root__: str
|
|
|
|
|
|
chain = chain.with_types(input_type=Question)
|