Anton_wireframe/app/__pycache__/main.cpython-312.pyc

Ë
Z
i{ãó¸—dd
lZdd
l
Z
dd
lZdd
lZddlmZmZmZ
ddl	m
Z

ddlmZm
Z
mZmZ
ddlmZ
ddlmZmZmZmZmZmZ
ddlmZmZmZ
ddlmZ
dd	lm Z 
dd
l!m"Z"
e
«
d„Z#e#«
e«Z$Gd„d
e«Z%Gd„de«Z&e$jOd«
d„«Z(e$jSddg
e*e+¬«e
d«
ed«
fdedede,fd„«Z-e$jSdeedg
¬«de%fd„«Z.e$jSdeedg
¬«de&fd „«Z/e$jaejb«

e$jaejb«

e$jaejb«

e$jaejb«

e$jaejb«

e$jaejb«

e2d!k(rdd
l3Z3e3jhd"d#d$¬%«
y
y
)&éN)ÚBaseÚ
db_dependencyÚengine)
Úload_dotenv)ÚFastAPIÚFileÚFormÚ
UploadFile)
Ú	BaseModel)Ú	companiesÚfolk_crmÚ
insight_routeÚ	investorsÚprojectsÚreport_route)ÚCompanyDataÚInvestmentResponseÚPaginatedResponse)
ÚCompanyQueryProcessor)
ÚInvestorProcessor)
ÚQueryProcessorcóL—tjjt¬
«

y)z.Initialize the database by creating all tables)
ÚbindN)rÚmetadataÚ
create_allr©óú?/home/oluwasanmi/Documents/Work/MKD/anton_wireframe/app/main.pyÚ
init_databasers€ä‡M�M×Ѥ&ÐÕ)rcó,—eZ
dZUeed
<Gd„d«Zy)ÚQueryRequestÚquestioncó—eZ
dZd
ddi
i
Zy)úQueryRequest.ConfigÚexampler"zDFind me deep tech investors that do deals in Europe under 5 million.N©Ú__name__Ú
__module__Ú__qualname__Újson_schema_extrarrrÚConfigr$(s„àØÐbðð
Ñrr+N©r'r(r)ÚstrÚ__annotations__r+rrrr!r!%ó…؃M÷
ò
rr!có,—eZ
dZUeed
<Gd„d«Zy)ÚCompanyQueryRequestr"có—eZ
dZd
ddi
i
Zy)úCompanyQueryRequest.Configr%r"zAFind me companies in the fintech sector located in San Francisco.Nr&rrrr+r32s„àØÐ_ðð
Ñrr+Nr,rrrr1r1/r/rr1ú
/có
—d
di
S)NÚHelloÚWorldrrrrÚhealthr89s
€à�WÐÐrz
/parse-csvz
CSV Upload)ÚtagsÚresponse_model.ÚdbÚfileÚis_investorcƒóF
K
—|
j
«ƒd
{–—†}tjtj|jd«
«
«
}t
«}|dk(r|j|d¬«ƒd
{–—†}|S|j|d¬«ƒd
{–—†}|S7Œ„7Œ%7Œ
­w
)a{
    Parse and import CSV data into the database.

    **For investors:**
    - Expected columns: Name, Website, Final Investor Profile, Final Profile sourcing
    - Manually parses JSON profiles for efficiency
    - Uses LLM only for currency conversion to USD
    - Handles AUM, fund sizes, and check sizes as integers

    **For companies:**
    - Expected columns: Name, Website, Perplexity Gap Output (or Final Investor Profile)
    - 100% manual JSON parsing - no LLM needed
    - **Only extracts:** founded_year and key_executives
    - **Only updates companies already in the database** (syncs with existing records)
    - Skips companies not found in the database

    **Benefits:**
    - Fast processing (5-10s per record)
    - Low cost (minimal or no LLM usage)
    - Accurate data extraction
    - Automatic database persistence
    - Safe: won't create duplicate companies
    Nzutf-8é
T)
Ú
save_to_db)	ÚreadÚpdÚread_csvÚioÚStringIOÚdecoderÚparse_investorsÚparse_companies)r;r<r=ÚcontentÚdfÚ	processorÚresultss       rÚ	parse_csvrM>s—èø€ð8—I‘I“K×€GÜ	�‰”R—[‘[ §¡°Ó!8Ó9Ó	:€Bô"Ó#€Ià�aÒà!×1Ñ1°"ÀÐ1ÓF×Fˆàˆð"×1Ñ1°"ÀÐ1ÓF×Fˆàˆð øðG
øð
G
ús4‚B!
–
B—A B!
Á7
BÁ8B!
Â
BÂB!
Â
B!
Â
B!
z/queryÚQuerying)r:r9Úrequestc
ƒóXK
—t
«}
|
j|j«
}|S­w
)
aŒ

    Query investors using natural language.

    Returns fund-level matches (one row per fund) with investor details.
    This ensures only relevant funds are included in the response.

    Supports queries like:
    - "Show me seed stage investors"
    - "Find fintech investors in Silicon Valley"
    - "Growth stage investors with $5M+ check sizes"
    - "Healthcare investors in Europe"
    )rÚ
process_queryr"©rOrKrLs   rÚquery_investorsrSls+èø€ô Ó €IØ×%Ñ% g×&6Ñ&6Ó7€GØ€Nùó‚(*
z/query-companiesc
ƒóXK
—t
«}
|
j|j«
}|S­w
)
a’

    Query companies using natural language.

    Returns company matches with their investor relationships, team members, and sectors.

    Supports queries like:
    - "Show me fintech companies founded in 2020"
    - "Find healthcare companies in San Francisco"
    - "Companies in the AI sector"
    - "Companies that received funding from Sequoia"