Tomaz Bratanic fd866d1801 Update Cypher QA prompt (#5173) ...

# Improve Cypher QA prompt

The current QA prompt is optimized for networkX answer generation, which
returns all the possible triples.
However, Cypher search is a bit more focused and doesn't necessary
return all the context information.
Due to that reason, the model sometimes refuses to generate an answer
even though the information is provided:

![Screenshot from 2023-05-24
08-36-23](https://github.com/hwchase17/langchain/assets/19948365/351cf9c1-2567-447c-91fd-284ae3fa1ccf)


To fix this issue, I have updated the prompt. Interestingly, I tried
many variations with less instructions and they didn't work properly.
However, the current fix works nicely.
![Screenshot from 2023-05-24
08-37-25](https://github.com/hwchase17/langchain/assets/19948365/fc830603-e6ec-4a23-8a86-eaf572996014)

2023-05-24 08:31:30 -07:00

..

api

Add _type for all parsers (#4189)

2023-05-11 01:27:58 -07:00

chat_vector_db

WIP: Harrison/base retriever (#1765)

2023-03-24 07:46:49 -07:00

combine_documents

Reuse length_func in MapReduceDocumentsChain (#5181)

2023-05-24 08:28:37 -07:00

constitutional_ai

Harrison/unified objectives (#4905)

2023-05-17 23:03:57 -07:00

conversation

Router chains (#4019)

2023-05-03 22:02:55 -07:00

conversational_retrieval

preserve language in conversation retrieval (#4969)

2023-05-21 21:16:03 -07:00

flare

WIP: FLARE-inspired chain (#4612)

2023-05-13 09:28:28 -07:00

graph_qa

Update Cypher QA prompt (#5173)

2023-05-24 08:31:30 -07:00

hyde

Replace remaining usage of basellm with baselangmodel (#3981)

2023-05-02 21:52:29 -07:00

llm_bash

Add _type for all parsers (#4189)

2023-05-11 01:27:58 -07:00

llm_checker

Replace remaining usage of basellm with baselangmodel (#3981)

2023-05-02 21:52:29 -07:00

llm_math

Improve math chain error msg (#4415)

2023-05-10 01:08:01 -07:00

llm_summarization_checker

fix typos in the prompts of LLMSummarizationCheckerChain (#4518)

2023-05-11 10:32:34 -07:00

natbot

Replace remaining usage of basellm with baselangmodel (#3981)

2023-05-02 21:52:29 -07:00

pal

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

qa_generation

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

qa_with_sources

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

query_constructor

Harrison/add top k (#4707)

2023-05-15 09:09:22 -07:00

question_answering

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

retrieval_qa

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

router

add embedding router (#4644)

2023-05-13 21:47:01 -07:00

sql_database

Replaced SQLDatabaseChain deprecated direct initialisation with from_llm method (#4778)

2023-05-16 15:59:06 -07:00

summarize

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

__init__.py

Harrison/neo4j (#5078)

2023-05-22 07:31:48 -07:00

base.py

fix json saving, update docs to reference anthropic chat model (#4364)

2023-05-08 15:30:52 -07:00

llm_requests.py

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

llm.py

fix: agenerate miss run_manager args in llm.py (#4566)

2023-05-16 17:37:56 -07:00

loading.py

Replaced SQLDatabaseChain deprecated direct initialisation with from_llm method (#4778)

2023-05-16 15:59:06 -07:00

mapreduce.py

Replace remaining usage of basellm with baselangmodel (#3981)

2023-05-02 21:52:29 -07:00

moderation.py

changed ValueError to ImportError (#5103)

2023-05-22 15:24:45 -07:00

prompt_selector.py

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

sequential.py

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00

transform.py

Callbacks Refactor [base] (#3256)

2023-04-30 11:14:09 -07:00